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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MLE
    -0.07
    VT
    -0.07
    H
    -0.07
     ejercicio
    -0.07
    Nem
    -0.07
     unge
    -0.07
    Keyboard
    -0.07
     protegido
    -0.07
    اض
    -0.07
     ਨਾ
    -0.07
    POSITIVE LOGITS
     Pioneer
    0.10
    ôtels
    0.09
     Trump
    0.08
     loyal
    0.08
     Trump's
    0.08
     scén
    0.08
     كوم
    0.08
    ahamwe
    0.08
    bury
    0.08
    rée
    0.08
    Act Density 0.000%

    No Known Activations