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

    Neuronpedia

    INDEX
    Explanations

    probability distributions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Planning
    -0.07
    ип
    -0.07
    ━
    -0.07
     Justin
    -0.07
    _three
    -0.07
     gentleman
    -0.07
    757
    -0.06
     structure
    -0.06
     decay
    -0.06
     succeed
    -0.06
    POSITIVE LOGITS
     رئيس
    0.06
     alo
    0.06
     una
    0.06
    唇
    0.06
    entionPolicy
    0.06
    (conv
    0.06
     đào
    0.06
    .con
    0.06
     "{$
    0.06
     tenía
    0.05
    Act Density 0.123%

    No Known Activations