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

    Neuronpedia

    INDEX
    Explanations

    _to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Income
    -0.06
    ):↵
    -0.06
    aunch
    -0.06
    Transfer
    -0.06
     mathematics
    -0.06
    ，以
    -0.06
     Access
    -0.06
    弃
    -0.06
     bunny
    -0.06
     flashing
    -0.06
    POSITIVE LOGITS
     Ελλά
    0.07
     administer
    0.06
    _clk
    0.06
    ิค
    0.06
     candidacy
    0.06
     Kirk
    0.06
     GetType
    0.06
     subparagraph
    0.06
    ku
    0.06
    customize
    0.06
    Act Density 0.003%

    No Known Activations