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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    獸
    -0.07
    犴
    -0.07
     inputStream
    -0.06
    master
    -0.06
     Erf
    -0.06
     Potion
    -0.06
    .second
    -0.06
    啸
    -0.06
     seizing
    -0.06
     invaders
    -0.06
    POSITIVE LOGITS
    %%*/
    0.07
    LLU
    0.07
     rebuild
    0.07
    עביר
    0.07
     nive
    0.06
     mogła
    0.06
     UK
    0.06
     الحكومة
    0.06
     Hã
    0.06
     Púb
    0.06
    Act Density 0.005%

    No Known Activations