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

    Neuronpedia

    INDEX
    Explanations

    uity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dive
    -0.07
    اصر
    -0.07
    audit
    -0.06
    HTTPS
    -0.06
    .published
    -0.06
    .sync
    -0.06
     advisory
    -0.06
     squat
    -0.06
     �
    -0.06
    prehensive
    -0.06
    POSITIVE LOGITS
    料
    0.07
    .pb
    0.06
    elah
    0.06
    (food
    0.06
    .tif
    0.06
     concessions
    0.06
     plag
    0.06
    意思
    0.06
    )(*
    0.06
    32
    0.06
    Act Density 0.000%

    No Known Activations