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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     loom
    -0.07
     CEP
    -0.07
     obstruct
    -0.07
     איש
    -0.07
     ποι
    -0.07
     reeds
    -0.07
     playoffs
    -0.06
    �
    -0.06
    ুভ
    -0.06
     threatening
    -0.06
    POSITIVE LOGITS
     subito
    0.10
     Затем
    0.09
     repeatedly
    0.09
     తరువాత
    0.09
     પછી
    0.08
     ardından
    0.08
     Потом
    0.08
     ನಂತರ
    0.08
     succeeded
    0.08
     తర్వాత
    0.08
    Act Density 0.036%

    No Known Activations