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

    Neuronpedia

    INDEX
    Explanations

    questions and reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    jf
    -0.07
    throws
    -0.06
    _comm
    -0.06
    .Level
    -0.06
    urre
    -0.06
    prior
    -0.06
    .lifecycle
    -0.06
    .reject
    -0.06
     ruins
    -0.06
    InputElement
    -0.06
    POSITIVE LOGITS
    adesh
    0.07
    ’ét
    0.07
    ????????
    0.07
     أنه
    0.06
    antis
    0.06
     miesz
    0.06
    endant
    0.06
     обов
    0.06
     krás
    0.06
     sosyal
    0.06
    Act Density 0.074%

    No Known Activations