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

    Neuronpedia

    INDEX
    Explanations

    expressions of comparison and differentiation in thought or belief systems

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

    not so much as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oredCriteria
    -0.79
    脚注の使い方
    -0.76
     للمعارف
    -0.74
    MessageTagHelper
    -0.72
    tagHelperRunner
    -0.69
    RenderAtEndOf
    -0.67
     surla
    -0.67
     mergeFrom
    -0.65
    AddTagHelper
    -0.63
    Portale
    -0.61
    POSITIVE LOGITS
    むしろ
    0.26
     скорее
    0.26
     than
    0.26
     saja
    0.25
     surtout
    0.24
     quoique
    0.24
    何より
    0.24
     아니라
    0.24
     souci
    0.23
    Deadpool
    0.23
    Act Density 0.092%

    No Known Activations