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

    Neuronpedia

    INDEX
    Explanations

    fl

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     probabil
    -0.06
    urtle
    -0.06
     Heg
    -0.06
    ar
    -0.06
    teenth
    -0.06
     LIABILITY
    -0.06
    serde
    -0.06
    avourite
    -0.06
     labour
    -0.06
     Cameron
    -0.06
    POSITIVE LOGITS
     Accessed
    0.08
     equ
    0.07
     πό
    0.06
    กำ
    0.06
     negatives
    0.06
    473
    0.06
    Immediately
    0.06
    LEAN
    0.06
    .Compile
    0.06
    lifting
    0.06
    Act Density 0.015%

    No Known Activations