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

    Neuronpedia

    INDEX
    Explanations

    lyrical

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "E
    -0.07
    ᴼ
    -0.07
    ="{
    -0.07
    这块
    -0.06
    ){}↵
    -0.06
     parms
    -0.06
     (::
    -0.06
     argc
    -0.06
     WTO
    -0.06
     String
    -0.06
    POSITIVE LOGITS
    _CHANNELS
    0.07
    Nd
    0.07
    友善
    0.07
    FONT
    0.07
    藿
    0.07
     Far
    0.07
    VICES
    0.07
    (Optional
    0.06
    עיד
    0.06
     объект
    0.06
    Act Density 0.030%

    No Known Activations