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

    Neuronpedia

    INDEX
    Explanations

    punctuation/symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Class
    -0.07
     pulls
    -0.07
    .Model
    -0.06
    _sh
    -0.06
    Ч
    -0.06
     R
    -0.06
     Milo
    -0.06
     COMMENT
    -0.06
    listeners
    -0.06
     cle
    -0.06
    POSITIVE LOGITS
    kHz
    0.07
     corpo
    0.06
    ดวก
    0.06
    iêm
    0.06
     レディース
    0.06
    정부
    0.06
     vibrations
    0.06
     ~=
    0.06
    ==>
    0.06
    овий
    0.06
    Act Density 0.023%

    No Known Activations