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

    Neuronpedia

    INDEX
    Explanations

    serial numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     survey
    -0.07
     Survey
    -0.06
    observe
    -0.06
     hey
    -0.06
     banking
    -0.06
    Survey
    -0.06
     ワ
    -0.06
    "You
    -0.06
     hasta
    -0.06
     zku
    -0.06
    POSITIVE LOGITS
    ічна
    0.06
    arseille
    0.06
    ued
    0.06
    ài
    0.06
    治
    0.06
    paRepository
    0.06
    (DWORD
    0.06
    증금
    0.06
    (FLAGS
    0.06
     sponsored
    0.06
    Act Density 0.032%

    No Known Activations