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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Phi
    -0.06
    PCODE
    -0.06
     Kami
    -0.06
    ฤษ
    -0.06
    Hall
    -0.06
     Kültür
    -0.06
    critical
    -0.06
     equity
    -0.06
    Orientation
    -0.06
     dáng
    -0.06
    POSITIVE LOGITS
    ']}
    0.07
     Saf
    0.06
     elaborate
    0.06
    die
    0.06
    }}}
    0.05
    (withIdentifier
    0.05
    Chars
    0.05
     Predict
    0.05
    Mock
    0.05
    _ask
    0.05
    Act Density 0.011%

    No Known Activations