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

    Neuronpedia

    INDEX
    Explanations

    technical specifications and measurements

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

    Increased levels or amplification

    np_acts-logits-general · gemini-2.0-flash

    increase, escalation, amplification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SEMICOLON
    -0.49
    HttpDelete
    -0.48
     Save
    -0.47
    Exited
    -0.47
     Kho
    -0.47
     Abigail
    -0.47
     save
    -0.47
     saved
    -0.46
    save
    -0.45
    batik
    -0.45
    POSITIVE LOGITS
     increase
    1.56
    increase
    1.44
    Increase
    1.40
     increases
    1.39
     Increase
    1.39
    Increases
    1.32
     Increases
    1.32
     increased
    1.30
    increases
    1.27
     INCREASE
    1.26
    Act Density 1.247%

    No Known Activations