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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     AWS
    -0.06
    ФЛ
    -0.06
     VX
    -0.06
     можуть
    -0.06
    468
    -0.06
     transmitted
    -0.06
    ."\
    -0.06
    /free
    -0.06
    undefined
    -0.06
    _cols
    -0.06
    POSITIVE LOGITS
    рап
    0.07
    olver
    0.07
     minist
    0.07
     conforme
    0.07
    .uml
    0.07
     trolls
    0.07
    MenuStrip
    0.06
    illing
    0.06
    ές
    0.06
    dorf
    0.06
    Act Density 0.007%

    No Known Activations