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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hawth
    -0.07
    ิ่
    -0.07
    ель
    -0.07
    _BINDING
    -0.06
    اشت
    -0.06
    inds
    -0.06
    _palette
    -0.06
     (↵↵
    -0.06
     '--
    -0.06
    igth
    -0.06
    POSITIVE LOGITS
    -wow
    0.06
    Helpers
    0.06
    Obsolete
    0.06
     Angle
    0.06
     Dover
    0.06
    (Action
    0.06
    액
    0.06
     Lafayette
    0.06
    Choices
    0.05
     LEN
    0.05
    Act Density 0.033%

    No Known Activations