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

    Neuronpedia

    INDEX
    Explanations

    insert

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jugador
    -0.07
     mutual
    -0.07
    ί
    -0.07
    しまった
    -0.07
     nursing
    -0.07
    awe
    -0.07
     anchored
    -0.07
    раст
    -0.07
     мн
    -0.07
     наприклад
    -0.06
    POSITIVE LOGITS
     Custom
    0.06
     handwritten
    0.06
    _$_
    0.06
     <<<
    0.06
    عال
    0.06
     antis
    0.06
    \xa
    0.06
    arie
    0.06
    يير
    0.06
     هواپیم
    0.06
    Act Density 0.006%

    No Known Activations