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
     Petro
    -0.08
    ounce
    -0.07
    айд
    -0.07
    游击队
    -0.07
     yr
    -0.07
    ville
    -0.07
     volunte
    -0.07
    ヂ
    -0.06
    仑
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    语法
    0.07
    Environmental
    0.07
     Daughter
    0.07
    añ
    0.06
     ties
    0.06
    adf
    0.06
    ATALOG
    0.06
    Nonce
    0.06
    DIV
    0.06
    父母
    0.06
    Act Density 0.051%

    No Known Activations