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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    istani
    -0.07
    레이
    -0.07
    胶
    -0.06
    vanced
    -0.06
    -Semit
    -0.06
    zers
    -0.06
     угод
    -0.06
    @Resource
    -0.06
     vant
    -0.06
     santa
    -0.06
    POSITIVE LOGITS
     pictures
    0.08
    ]):
    0.07
     praises
    0.07
     static
    0.06
    mez
    0.06
     omnip
    0.06
    ’)
    0.06
    Maps
    0.06
    }-
    0.06
     Libyan
    0.06
    Act Density 0.002%

    No Known Activations