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

    Neuronpedia

    INDEX
    Explanations

    .shape

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ⟡
    -0.07
    oned
    -0.07
     따
    -0.07
    di
    -0.07
     torture
    -0.07
    legates
    -0.07
    AndView
    -0.07
    nd
    -0.07
    apped
    -0.07
    甜甜
    -0.07
    POSITIVE LOGITS
    POINTS
    0.06
    /msg
    0.06
     Ку
    0.06
    _phrase
    0.06
    理工大学
    0.06
     memorandum
    0.06
    	L
    0.06
    瘾
    0.06
    .origin
    0.06
    _CODE
    0.06
    Act Density 0.004%

    No Known Activations