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

    Neuronpedia

    INDEX
    Explanations

    new followed by type

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mods
    0.39
    ،
    0.39
    odată
    0.38
     बजा
    0.37
    ﾁ
    0.37
    irti
    0.36
    列
    0.36
     mags
    0.35
     psig
    0.35
     generics
    0.35
    POSITIVE LOGITS
     {
    0.53
    (){
    0.44
     Angebote
    0.42
    ?
    0.42
     Schott
    0.41
    ocation
    0.41
    !
    0.38
    yect
    0.38
     (){
    0.38
     Which
    0.37
    Act Density 0.028%

    No Known Activations