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

    Neuronpedia

    INDEX
    Explanations

    lasers and amplifiers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    —which
    -0.07
    asin
    -0.06
    kate
    -0.06
     mankind
    -0.06
    ?“
    -0.06
     communications
    -0.06
    -------
    -0.06
     Communication
    -0.06
    _CODES
    -0.06
     baking
    -0.06
    POSITIVE LOGITS
     PERF
    0.06
    .med
    0.06
     нія
    0.06
     naar
    0.06
     otherButtonTitles
    0.06
    に向
    0.06
     trest
    0.06
    toPromise
    0.06
    �
    0.06
     응
    0.06
    Act Density 0.017%

    No Known Activations