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

    Neuronpedia

    INDEX
    Explanations

    colons, bracketed numbers, and the word "return" in code.

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    not
    -0.53
    of
    -0.52
    vo
    -0.50
    Revenir
    -0.50
    ante
    -0.49
    chi
    -0.49
    mer
    -0.48
    v
    -0.48
    ens
    -0.48
    with
    -0.48
    POSITIVE LOGITS
    ICAGO
    1.01
     RSITY
    0.91
    ^(@)
    0.90
     photolibrary
    0.90
     ERSITY
    0.85
     pngtree
    0.85
     myſelf
    0.85
     houſe
    0.84
     themſelves
    0.82
     doubtnut
    0.82
    Act Density 4.554%

    No Known Activations