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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .sav
    -0.07
    verse
    -0.07
    _fail
    -0.06
     Zeus
    -0.06
     bac
    -0.06
    _alpha
    -0.06
     singular
    -0.06
    mun
    -0.06
    775
    -0.06
    }:
    -0.06
    POSITIVE LOGITS
     centres
    0.07
    .spawn
    0.06
    }")↵↵
    0.06
    _Al
    0.06
     Grade
    0.06
    _fake
    0.06
    _KHR
    0.06
    Ter
    0.06
    Mike
    0.06
     Ter
    0.06
    Act Density 0.319%

    No Known Activations