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

    Neuronpedia

    INDEX
    Explanations

    call

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tears
    -0.07
     insured
    -0.07
    摸
    -0.07
     stuffed
    -0.07
    attended
    -0.07
    🇿
    -0.06
    可想
    -0.06
    rell
    -0.06
    焜
    -0.06
    𝑲
    -0.06
    POSITIVE LOGITS
     rehab
    0.07
     Hurricane
    0.07
    Hooks
    0.07
     apache
    0.07
     الثنائية
    0.06
    .iterator
    0.06
    .Country
    0.06
     gauche
    0.06
     Jab
    0.06
    toMatchSnapshot
    0.06
    Act Density 0.001%

    No Known Activations