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

    Neuronpedia

    INDEX
    Explanations

    ly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     factions
    -0.06
    Max
    -0.06
     Dag
    -0.06
    "L
    -0.06
    _mono
    -0.06
     kav
    -0.06
    (@
    -0.06
     sect
    -0.06
     samo
    -0.06
    _corr
    -0.06
    POSITIVE LOGITS
    開
    0.07
     guiding
    0.07
     hit
    0.07
    .struts
    0.07
    Stopped
    0.07
    NewUrlParser
    0.06
    Science
    0.06
    思い
    0.06
    sl
    0.06
     mistake
    0.06
    Act Density 0.007%

    No Known Activations