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

    Neuronpedia

    INDEX
    Explanations

    Academic/research articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dar
    -0.07
     destin
    -0.07
    cky
    -0.07
     charities
    -0.07
    ั่
    -0.06
    uppercase
    -0.06
    功
    -0.06
     �
    -0.06
    iêm
    -0.06
     contaminated
    -0.06
    POSITIVE LOGITS
    phen
    0.07
    _BOUNDS
    0.06
    (phase
    0.06
    )↵↵↵
    0.06
    SCRI
    0.06
    -m
    0.06
    _Max
    0.06
     OPTIONAL
    0.06
    France
    0.06
    उ
    0.06
    Act Density 0.350%

    No Known Activations