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
    conditionally
    -0.08
     Voor
    -0.07
     Combination
    -0.07
    营
    -0.07
     pill
    -0.06
     NSDictionary
    -0.06
     Für
    -0.06
    control
    -0.06
     davran
    -0.06
     protagonists
    -0.06
    POSITIVE LOGITS
     GN
    0.06
    梯
    0.06
    (acc
    0.06
    ginas
    0.06
    (bg
    0.06
    tain
    0.06
    PARAM
    0.06
    �
    0.06
    iquer
    0.06
    											↵
    0.06
    Act Density 0.026%

    No Known Activations