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

    Neuronpedia

    INDEX
    Explanations

    ()

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _season
    -0.08
    唢
    -0.07
    utowired
    -0.07
     Sche
    -0.07
     ш
    -0.07
     дл
    -0.07
     strife
    -0.07
     dette
    -0.07
    加紧
    -0.07
     leash
    -0.07
    POSITIVE LOGITS
     Connector
    0.08
    _RESULT
    0.07
    uality
    0.07
    png
    0.07
    CF
    0.07
     rebels
    0.07
    (project
    0.07
    KG
    0.07
    emergency
    0.06
    PR
    0.06
    Act Density 0.004%

    No Known Activations