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

    Neuronpedia

    INDEX
    Explanations

    submit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    中科院
    -0.07
    irit
    -0.07
    �
    -0.07
    HG
    -0.07
    🍞
    -0.06
     Cir
    -0.06
    -good
    -0.06
     Woman
    -0.06
    York
    -0.06
    mour
    -0.06
    POSITIVE LOGITS
    statement
    0.07
     prostate
    0.07
    _SLAVE
    0.07
     người
    0.07
     constituent
    0.07
     contracts
    0.06
     devil
    0.06
    גב
    0.06
    >/<
    0.06
     restTemplate
    0.06
    Act Density 0.006%

    No Known Activations