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

    Neuronpedia

    INDEX
    Explanations

    honey

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Layer
    -0.07
     nineteenth
    -0.06
     Spaces
    -0.06
    災
    -0.06
     mong
    -0.06
    .BatchNorm
    -0.06
    	layer
    -0.06
    EMU
    -0.06
    ARSE
    -0.06
     compan
    -0.06
    POSITIVE LOGITS
     honey
    0.07
     pleas
    0.06
    担当
    0.06
    点
    0.06
     používá
    0.06
    Bài
    0.06
     beim
    0.06
    .Handler
    0.06
     Hmm
    0.06
    ►
    0.06
    Act Density 0.002%

    No Known Activations