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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     launching
    -0.07
     CharSequence
    -0.06
     bacon
    -0.06
    _particles
    -0.06
    ующих
    -0.06
    "|
    -0.06
     irresistible
    -0.06
    .Foundation
    -0.06
     зов
    -0.06
     Mỹ
    -0.06
    POSITIVE LOGITS
    -tra
    0.09
    rose
    0.07
     rely
    0.07
    ión
    0.06
    одар
    0.06
     ortaya
    0.06
    quota
    0.06
     utilizar
    0.06
    ÃO
    0.06
    .kafka
    0.06
    Act Density 0.024%

    No Known Activations