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

    Neuronpedia

    INDEX
    Explanations

    say Output

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    孔
    -0.07
    Kind
    -0.07
    一下
    -0.06
    -ups
    -0.06
    Shock
    -0.06
    *L
    -0.06
    *w
    -0.06
     prayer
    -0.06
    ̉
    -0.06
    ρχ
    -0.06
    POSITIVE LOGITS
     tactile
    0.07
    рім
    0.06
     funkci
    0.06
    .single
    0.06
    .Axis
    0.06
    .getTable
    0.06
    enabled
    0.06
     місцев
    0.06
     Ammo
    0.06
    規
    0.06
    Act Density 0.070%

    No Known Activations