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

    Neuronpedia

    INDEX
    Explanations

    function signatures with braces `{`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಾಲ
    0.40
    بيب
    0.37
    醯
    0.36
    寺
    0.36
    濾
    0.36
     সিলে
    0.35
    gangenheit
    0.35
    efficacy
    0.35
    萄
    0.35
     சைவ
    0.34
    POSITIVE LOGITS
     {
    0.77
     ->
    0.65
     throws
    0.61
     =>
    0.57
     =>{
    0.49
    throws
    0.48
     =
    0.48
    ){
    0.47
     ){
    0.47
    (){
    0.47
    Act Density 0.022%

    No Known Activations