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

    Neuronpedia

    INDEX
    Explanations

    copy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mountains
    -0.07
    getIndex
    -0.06
    losure
    -0.06
     potentials
    -0.06
     realmente
    -0.06
    、い
    -0.06
    Serialize
    -0.06
     fores
    -0.06
    属
    -0.06
    emente
    -0.06
    POSITIVE LOGITS
    ']/
    0.07
    <dd
    0.06
    人民
    0.06
    %@
    0.06
     AudioClip
    0.06
    Eth
    0.06
    ayne
    0.06
     teenager
    0.06
     INTERN
    0.06
     Goku
    0.06
    Act Density 0.002%

    No Known Activations