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

    Neuronpedia

    INDEX
    Explanations

    Oracle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     attest
    -0.07
     pentru
    -0.07
    Master
    -0.07
     brigade
    -0.07
     Garner
    -0.07
    为一体的
    -0.07
     fed
    -0.07
     Phaser
    -0.07
    ኣ
    -0.07
     ספר
    -0.06
    POSITIVE LOGITS
     slowdown
    0.07
    *m
    0.07
    *s
    0.07
    榨
    0.07
    💸
    0.07
     Uploaded
    0.06
    *z
    0.06
     sexism
    0.06
    ~~~~~~~~
    0.06
    olesale
    0.06
    Act Density 0.002%

    No Known Activations