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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     parenthesis
    -0.07
    犬
    -0.06
     compete
    -0.06
    cox
    -0.06
     drinkers
    -0.06
    ovic
    -0.06
    _decoder
    -0.06
    比
    -0.06
     Compute
    -0.06
     Clare
    -0.06
    POSITIVE LOGITS
     أب
    0.07
     erotici
    0.07
    вався
    0.07
    และส
    0.06
    Common
    0.06
     enforcing
    0.06
     köy
    0.06
    omm
    0.06
     overlay
    0.06
     intf
    0.06
    Act Density 0.058%

    No Known Activations