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

    Neuronpedia

    INDEX
    Explanations

    they

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Flying
    -0.06
    angan
    -0.06
     María
    -0.06
    andro
    -0.06
     Simpl
    -0.06
    Reality
    -0.06
     Intercept
    -0.06
    morph
    -0.06
     کال
    -0.06
    faf
    -0.06
    POSITIVE LOGITS
    StatusBar
    0.08
     they
    0.07
     استاند
    0.07
     треб
    0.06
    —I
    0.06
    fortawesome
    0.06
     marin
    0.06
    .Errorf
    0.06
     {%
    0.06
    ckett
    0.06
    Act Density 0.204%

    No Known Activations