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

    Neuronpedia

    INDEX
    Explanations

    security

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     corrid
    -0.06
    riends
    -0.06
    าท
    -0.06
    \Log
    -0.06
    来た
    -0.06
    weets
    -0.06
     Theta
    -0.06
     BOX
    -0.06
    диви
    -0.06
     projeto
    -0.06
    POSITIVE LOGITS
     InetAddress
    0.07
     моч
    0.07
     DAC
    0.07
     dataframe
    0.06
     intimidation
    0.06
    =>'
    0.06
    луш
    0.06
     plav
    0.06
    ندگی
    0.06
    AsStream
    0.06
    Act Density 0.015%

    No Known Activations