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
    ovaného
    -0.07
     теж
    -0.07
    .notifyDataSetChanged
    -0.07
     바랍니다
    -0.06
    vida
    -0.06
    _note
    -0.06
     Gus
    -0.06
    _ang
    -0.06
     أم
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     NORTH
    0.06
     corresponding
    0.06
     devour
    0.06
     Crack
    0.06
     Hey
    0.06
     references
    0.06
     Quarter
    0.06
     Interested
    0.06
     NOTICE
    0.06
    ................
    0.06
    Act Density 0.496%

    No Known Activations