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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lik
    -0.08
     Asians
    -0.07
    יצוב
    -0.07
    .Automation
    -0.07
    慌
    -0.07
     Okay
    -0.06
    agina
    -0.06
    慰
    -0.06
     ز
    -0.06
     atoms
    -0.06
    POSITIVE LOGITS
     /\
    0.07
    fork
    0.07
    굄
    0.07
    .NEW
    0.07
    drv
    0.07
    .root
    0.06
    Enumer
    0.06
     bảng
    0.06
    靶
    0.06
    /right
    0.06
    Act Density 0.043%

    No Known Activations