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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sensors
    -0.07
    eth
    -0.07
     another
    -0.07
     drug
    -0.06
     explaining
    -0.06
     requesting
    -0.06
     artisan
    -0.06
    ství
    -0.06
    irma
    -0.06
    igate
    -0.06
    POSITIVE LOGITS
     newPassword
    0.07
     tròn
    0.07
    [at
    0.07
     passphrase
    0.07
     Кри
    0.07
     GameController
    0.06
     shalt
    0.06
    /Runtime
    0.06
     paylaş
    0.06
     WHITE
    0.06
    Act Density 0.010%

    No Known Activations