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

    Neuronpedia

    INDEX
    Explanations

    pig

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     alpha
    -0.08
     曰
    -0.06
     resolver
    -0.06
     intimacy
    -0.06
    rear
    -0.06
    stress
    -0.06
     causes
    -0.06
     suç
    -0.06
     Rifle
    -0.06
     fullscreen
    -0.06
    POSITIVE LOGITS
     creatively
    0.07
    LAG
    0.07
    .isPresent
    0.07
    UNG
    0.07
    ailability
    0.06
    antic
    0.06
    茨
    0.06
    -cent
    0.06
    연
    0.06
    :function
    0.06
    Act Density 0.001%

    No Known Activations