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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    픽
    -0.07
    ामक
    -0.06
     Duffy
    -0.06
    อท
    -0.06
    альный
    -0.06
    ically
    -0.06
    .Ac
    -0.06
    energy
    -0.06
    No
    -0.06
    shake
    -0.06
    POSITIVE LOGITS
    caf
    0.07
     licences
    0.06
    ablish
    0.06
    ypy
    0.06
    süz
    0.06
    clude
    0.06
     sü
    0.06
    �ng
    0.06
    ”—
    0.06
    ?-
    0.06
    Act Density 0.000%

    No Known Activations