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

    Neuronpedia

    INDEX
    Explanations

    references to servers and related technologies

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

    following "server"

    np_acts-logits-general · gemini-2.0-flash

    server side error

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.67
    PerformLayout
    -0.66
    endforeach
    -0.64
    tagHelperRunner
    -0.62
    mergeFrom
    -0.62
     postIndex
    -0.59
    ⓧ
    -0.59
    ]")]
    -0.57
     تضيفلها
    -0.57
    المكان
    -0.54
    POSITIVE LOGITS
    side
    0.82
    wide
    0.81
     side
    0.78
    Side
    0.75
     wide
    0.71
     Side
    0.71
    WIDE
    0.67
     SIDE
    0.66
    specific
    0.64
    SIDE
    0.62
    Act Density 0.409%

    No Known Activations