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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    诞
    -0.07
    antine
    -0.07
    條
    -0.07
    /install
    -0.06
    𬘯
    -0.06
    _MAPPING
    -0.06
    non
    -0.06
     PSI
    -0.06
     registr
    -0.06
    臨
    -0.06
    POSITIVE LOGITS
     voluntary
    0.07
     textual
    0.07
     дерев
    0.07
    חיפוש
    0.07
     רוב
    0.07
    uent
    0.07
    _Search
    0.07
     Ax
    0.07
    شرو
    0.06
    ursive
    0.06
    Act Density 0.015%

    No Known Activations