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

    Neuronpedia

    INDEX
    Explanations

    calls to action for users to try or experiment with something

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

    Comes before "changing", "out", or "following"

    np_acts-logits-general · gemini-2.0-flash

    try and see

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ">+
    -0.55
    ]=$
    -0.52
    }{*}{}
    -0.52
     ∙
    -0.50
     perfectly
    -0.49
    ">—
    -0.48
    󠁣
    -0.48
    ">.
    -0.47
    perfectly
    -0.47
     Mase
    -0.47
    POSITIVE LOGITS
     kræ
    0.84
     MainAxisSize
    0.74
     out
    0.72
    Different
    0.71
     Different
    0.69
    different
    0.67
     GenerationType
    0.67
    évaluateur
    0.67
     different
    0.66
     Roskov
    0.65
    Act Density 0.086%

    No Known Activations