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
    lems
    -0.07
    reservation
    -0.06
    itions
    -0.06
     CV
    -0.06
     agreement
    -0.06
    盟
    -0.06
    操
    -0.06
    _version
    -0.06
    ventions
    -0.06
    ification
    -0.06
    POSITIVE LOGITS
     произош
    0.07
    iyordu
    0.06
     Garten
    0.06
     modelos
    0.06
     Shut
    0.06
    ازد
    0.06
     wides
    0.06
     acknow
    0.06
    .inf
    0.06
     bütün
    0.06
    Act Density 0.039%

    No Known Activations