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

    Neuronpedia

    INDEX
    Explanations

    health conditions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     модель
    -0.07
     quay
    -0.06
     quiere
    -0.06
     вог
    -0.06
    )];
    -0.06
    _model
    -0.06
    _INFINITY
    -0.06
     تحلیل
    -0.06
    .FLAG
    -0.06
     місто
    -0.06
    POSITIVE LOGITS
     peach
    0.06
    (Blueprint
    0.06
     şeyler
    0.06
     OpenFileDialog
    0.06
     Telefon
    0.06
    icho
    0.06
     Heller
    0.06
     Καρ
    0.06
     Rose
    0.06
     Secret
    0.06
    Act Density 0.110%

    No Known Activations