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
     nale
    -0.07
    _vertical
    -0.07
     Jul
    -0.07
     adultos
    -0.06
    rieb
    -0.06
    深
    -0.06
    तर
    -0.06
    alore
    -0.06
     yok
    -0.06
    اهرة
    -0.06
    POSITIVE LOGITS
     สามารถ
    0.07
    SDK
    0.07
     Premium
    0.07
    -param
    0.07
     meta
    0.06
    mi
    0.06
     jumping
    0.06
     Steve
    0.06
    .setAlignment
    0.06
     inducing
    0.06
    Act Density 0.018%

    No Known Activations