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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ucc
    -0.07
    会选择
    -0.07
    选址
    -0.07
     dị
    -0.07
    ims
    -0.07
     trustee
    -0.06
     prognosis
    -0.06
     hurd
    -0.06
     diagnosis
    -0.06
    😛
    -0.06
    POSITIVE LOGITS
    rogen
    0.07
    _YEAR
    0.07
    一带
    0.07
    _control
    0.07
    >*
    0.07
    Variable
    0.06
    概况
    0.06
    ,eg
    0.06
    俄国
    0.06
     Predicate
    0.06
    Act Density 0.006%

    No Known Activations