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

    Neuronpedia

    INDEX
    Explanations

    PowerShell scripts, packing lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sapphire
    0.43
    atelle
    0.43
    f
    0.42
    湖
    0.42
    inent
    0.41
    Brush
    0.41
    带
    0.40
    indentLevel
    0.40
    лах
    0.39
    变形
    0.39
    POSITIVE LOGITS
     COLLEGE
    0.47
    orithms
    0.46
     describir
    0.46
     Dwight
    0.46
     Dmit
    0.45
     resultlist
    0.44
     comunic
    0.43
     }}$,
    0.43
     endgame
    0.43
     ener
    0.43
    Act Density 0.000%

    No Known Activations