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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hattan
    -0.07
    ゴ
    -0.06
    h
    -0.06
    loyd
    -0.06
    agos
    -0.06
     người
    -0.06
     то
    -0.06
    asted
    -0.06
     levels
    -0.06
    enti
    -0.06
    POSITIVE LOGITS
     midway
    0.07
    _lbl
    0.06
     streamline
    0.06
    niej
    0.06
     booth
    0.06
     azal
    0.06
    "crypto
    0.06
     unintended
    0.06
     itm
    0.06
    और
    0.06
    Act Density 0.032%

    No Known Activations