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

    Neuronpedia

    INDEX
    Explanations

    exam

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -directory
    -0.08
     twice
    -0.07
    荣
    -0.07
     strip
    -0.07
    patient
    -0.07
     CU
    -0.07
    齊
    -0.07
     Monte
    -0.07
    を見
    -0.07
    𝘷
    -0.07
    POSITIVE LOGITS
     PlayerPrefs
    0.08
    lararası
    0.07
     damer
    0.07
    colm
    0.07
    .MODEL
    0.07
    ım
    0.07
    [strlen
    0.07
     timeval
    0.06
    屺
    0.06
    毛利率
    0.06
    Act Density 0.010%

    No Known Activations