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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     anger
    -0.07
    ама
    -0.07
    ylko
    -0.06
    мор
    -0.06
    通常
    -0.06
     defenses
    -0.06
     уровень
    -0.06
     яких
    -0.06
     logos
    -0.06
     quitting
    -0.06
    POSITIVE LOGITS
    .Euler
    0.07
    .asarray
    0.07
    _PER
    0.06
    �
    0.06
     PER
    0.06
    _ID
    0.06
    .setParent
    0.06
    _MENU
    0.06
    .freq
    0.06
    .herokuapp
    0.06
    Act Density 0.004%

    No Known Activations