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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks indicating interruptions or transitions in text

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

    Em dashes and dashes

    np_acts-logits-general · gemini-2.0-flash

    introduction of specifics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (?)
    -0.53
     (%)
    -0.48
    </>
    -0.48
    ̀nh
    -0.48
     sẻ
    -0.46
    ManyToOne
    -0.46
     stb
    -0.46
     (?
    -0.45
    reet
    -0.45
    DockStyle
    -0.44
    POSITIVE LOGITS
    albeit
    1.02
     albeit
    0.96
    including
    0.93
    except
    0.93
     namely
    0.92
     including
    0.91
    namely
    0.88
     hence
    0.88
    particularly
    0.88
    although
    0.87
    Act Density 0.116%

    No Known Activations