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

    Neuronpedia

    INDEX
    Explanations

    punctuation and common words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _CHK
    -0.07
     Зам
    -0.06
    ุต
    -0.06
    vsp
    -0.06
    _DSP
    -0.06
    AVE
    -0.06
     manageable
    -0.06
    Finance
    -0.06
     Deluxe
    -0.06
     Denmark
    -0.05
    POSITIVE LOGITS
     peny
    0.08
     cellpadding
    0.07
    [M
    0.07
     Jar
    0.07
     vita
    0.07
    ",(
    0.07
    _kernel
    0.07
     entitlement
    0.06
     melanch
    0.06
     "'.
    0.06
    Act Density 0.029%

    No Known Activations