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

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tensorflow
    -0.07
     steam
    -0.07
     Paz
    -0.07
     Klo
    -0.06
    .STATE
    -0.06
     muslim
    -0.06
    HOUSE
    -0.06
     Sebastian
    -0.06
     menn
    -0.06
    zech
    -0.06
    POSITIVE LOGITS
     Recall
    0.07
    Ⓓ
    0.07
    _normal
    0.06
     discs
    0.06
     Tonight
    0.06
     decid
    0.06
    (note
    0.06
    ENTS
    0.06
     opendir
    0.06
    иру
    0.06
    Act Density 0.023%

    No Known Activations