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

    Neuronpedia

    INDEX
    Explanations

    email headers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    imestone
    -0.07
     Bollywood
    -0.07
     '!
    -0.07
    “But
    -0.07
    疸
    -0.07
    passwd
    -0.06
    )),
    -0.06
     ROAD
    -0.06
    ("----------------
    -0.06
    .Stdout
    -0.06
    POSITIVE LOGITS
     Canon
    0.08
    CIÓN
    0.07
    ении
    0.07
    _methods
    0.07
    ATO
    0.07
     dici
    0.07
    CEL
    0.07
    antes
    0.07
     getParent
    0.07
     thưởng
    0.07
    Act Density 0.001%

    No Known Activations