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
    (IL
    -0.07
     LIC
    -0.06
     municipalities
    -0.06
     IB
    -0.06
    $.
    -0.06
     Bing
    -0.06
    773
    -0.06
     StringType
    -0.06
    =response
    -0.06
     INST
    -0.06
    POSITIVE LOGITS
    úmeros
    0.07
     electrodes
    0.07
     شهری
    0.06
    +#
    0.06
    ующий
    0.06
     şans
    0.06
     MPH
    0.06
     suốt
    0.06
    -picture
    0.06
     sorumlu
    0.06
    Act Density 0.007%

    No Known Activations