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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     charming
    -0.08
    	async
    -0.06
     груз
    -0.06
    .Must
    -0.06
     sensible
    -0.06
    	address
    -0.06
     deleted
    -0.06
     crates
    -0.06
    koneksi
    -0.06
    ComboBox
    -0.06
    POSITIVE LOGITS
    -layer
    0.07
    ดำ
    0.07
     mushroom
    0.07
     garnered
    0.07
    イク
    0.06
    _pcm
    0.06
    -band
    0.06
     exploiting
    0.06
    ám
    0.06
    没有
    0.06
    Act Density 0.037%

    No Known Activations