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

    Neuronpedia

    INDEX
    Explanations

    months

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     arithmetic
    -0.07
     blackmail
    -0.07
    (open
    -0.07
    .Keyword
    -0.07
     specific
    -0.07
    _PAIR
    -0.07
    /student
    -0.07
    _BOUND
    -0.07
     simple
    -0.07
     evapor
    -0.07
    POSITIVE LOGITS
    港
    0.07
    根底
    0.06
    CEE
    0.06
     hoped
    0.06
    绵
    0.06
     embraced
    0.06
    -private
    0.06
    团
    0.06
    掳
    0.06
    rega
    0.06
    Act Density 0.001%

    No Known Activations