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

    Neuronpedia

    INDEX
    Explanations

    special characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ToList
    -0.07
     immoral
    -0.07
    (mode
    -0.07
    og
    -0.07
     zeit
    -0.06
    第一
    -0.06
     جد
    -0.06
    .vert
    -0.06
     useCallback
    -0.06
    _PRODUCT
    -0.06
    POSITIVE LOGITS
     vh
    0.07
     ansible
    0.06
    hy
    0.06
     xf
    0.06
    ewire
    0.06
    �다
    0.06
    enaries
    0.06
     cpt
    0.06
    ุณ
    0.06
     grenades
    0.06
    Act Density 0.009%

    No Known Activations