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

    Neuronpedia

    INDEX
    Explanations

    constructor arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    id
    0.45
    引き続き
    0.44
     அவரின்
    0.40
    his
    0.37
    resizable
    0.36
     remind
    0.36
    o
    0.35
    Chinese
    0.35
    //
    0.35
    National
    0.34
    POSITIVE LOGITS
     टार
    0.46
     Déc
    0.46
     tule
    0.44
     இவ்வ
    0.43
    umping
    0.43
    úng
    0.41
     अफे
    0.41
     fæ
    0.41
     diese
    0.41
     embry
    0.40
    Act Density 0.015%

    No Known Activations