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

    Neuronpedia

    INDEX
    Explanations

    decide

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wd
    -0.07
    onium
    -0.07
    -loving
    -0.06
     rhyme
    -0.06
     Sikh
    -0.06
    .--
    -0.06
     necesita
    -0.06
    ecial
    -0.06
     sní
    -0.06
     Establishment
    -0.06
    POSITIVE LOGITS
     性
    0.07
    ILLS
    0.07
    ("")]↵
    0.06
    .route
    0.06
    ITTE
    0.06
     te
    0.06
    907
    0.06
     indices
    0.06
     LoginActivity
    0.06
    ετ
    0.06
    Act Density 0.014%

    No Known Activations