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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .newArrayList
    -0.07
     follando
    -0.07
     tolua
    -0.07
    /signup
    -0.07
     kå
    -0.07
    .which
    -0.07
     khung
    -0.07
    .chrome
    -0.07
    .mapper
    -0.07
     Kew
    -0.06
    POSITIVE LOGITS
    。“
    0.07
     infr
    0.06
    allah
    0.06
    awei
    0.06
    _Line
    0.06
    ’m
    0.06
     harming
    0.06
    rades
    0.06
    CEED
    0.05
    (PyObject
    0.05
    Act Density 0.036%

    No Known Activations