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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    unik
    -0.06
     NPC
    -0.06
     Mouth
    -0.06
    ､
    -0.06
    Telephone
    -0.06
    -{
    -0.06
     Scaffold
    -0.06
    __))
    -0.06
    uster
    -0.06
     make
    -0.06
    POSITIVE LOGITS
    اسي
    0.07
     colossal
    0.07
     امور
    0.07
     đêm
    0.06
     lor
    0.06
    istem
    0.06
     responseType
    0.06
    att
    0.06
     Tomáš
    0.06
    정부
    0.06
    Act Density 0.000%

    No Known Activations