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

    Neuronpedia

    INDEX
    Explanations

    therapy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    长长
    -0.08
     shack
    -0.07
    Ƞ
    -0.07
     liaison
    -0.06
    会会长
    -0.06
    ddie
    -0.06
    _interface
    -0.06
    怀抱
    -0.06
    瞄
    -0.06
    dbc
    -0.06
    POSITIVE LOGITS
     linen
    0.07
     Helping
    0.07
    小伙伴
    0.07
    -cut
    0.06
     (%)
    0.06
    	border
    0.06
    阐明
    0.06
    Fine
    0.06
    开场
    0.06
    dataset
    0.06
    Act Density 0.032%

    No Known Activations