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

    Neuronpedia

    INDEX
    Explanations

    Predictions and models

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     acknowledge
    -0.06
     names
    -0.06
    _air
    -0.06
    Kick
    -0.06
     theorem
    -0.06
    ека
    -0.06
     demon
    -0.06
    .mc
    -0.06
     valley
    -0.06
     Tree
    -0.06
    POSITIVE LOGITS
    �
    0.07
     yaptığı
    0.07
     lavor
    0.07
     новый
    0.06
    ULONG
    0.06
    련
    0.06
     nevě
    0.06
     عملکرد
    0.06
     रखन
    0.06
     společnosti
    0.06
    Act Density 0.028%

    No Known Activations