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

    Neuronpedia

    INDEX
    Explanations

    terms related to round shapes and objects

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

    round shapes and objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    $_['
    -0.39
     spesa
    -0.36
     powod
    -0.35
     Assistance
    -0.34
    pub
    -0.34
    Past
    -0.33
     rég
    -0.33
    Rest
    -0.33
    ngdoc
    -0.32
     hö
    -0.32
    POSITIVE LOGITS
     round
    0.58
    MessageOf
    0.58
    دانشنامهٔ
    0.58
    cheibe
    0.57
     ROUND
    0.56
    клопе
    0.54
     translucent
    0.54
     CanadaChoose
    0.54
     rounded
    0.54
    indrical
    0.53
    Act Density 0.012%

    No Known Activations