Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    instances of critical acclaim and recognition in film reviews

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Opinions, judgments, and expectations

    np_acts-logits-general · gemini-2.0-flash

    critical reception and expectations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hal
    -0.46
    вай
    -0.46
    del
    -0.40
    ry
    -0.39
    Subjects
    -0.39
    kelen
    -0.38
     Kimball
    -0.38
    ToolStripButton
    -0.37
     [*]
    -0.37
    タメ
    -0.37
    POSITIVE LOGITS
     consensus
    1.01
     Consensus
    1.00
    consensus
    0.90
    Consensus
    0.88
     Expectations
    0.87
     analysts
    0.86
     critics
    0.84
    expectations
    0.82
     reviewers
    0.82
     expectations
    0.82
    Act Density 0.166%

    No Known Activations