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

    Neuronpedia

    INDEX
    Explanations

    bypassing phone security

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     undocumented
    -0.08
     sports
    -0.08
     (~
    -0.07
     authentication
    -0.07
    -0.07
     {'
    -0.07
     आता
    -0.07
     pronunciation
    -0.07
    هم
    -0.07
     infection
    -0.07
    POSITIVE LOGITS
     cair
    0.09
     оставить
    0.09
     выб
    0.08
     Throwable
    0.08
     lançar
    0.08
    anzibar
    0.08
     σχέ
    0.08
     внеш
    0.08
     tiba
    0.08
    ancio
    0.08
    Act Density 0.000%
    No Known Activations