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

    Neuronpedia

    INDEX
    Explanations

    colon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (O
    -0.07
     여성
    -0.07
    (Window
    -0.06
    _white
    -0.06
    ,-
    -0.06
    โน
    -0.06
     INTER
    -0.06
    	be
    -0.06
    income
    -0.06
    /movie
    -0.06
    POSITIVE LOGITS
     NSW
    0.06
     journalistic
    0.06
     сказав
    0.06
    acement
    0.06
    attended
    0.06
    .netbeans
    0.06
     FormsModule
    0.06
    DSA
    0.06
    ्मच
    0.06
    킹
    0.06
    Act Density 0.003%

    No Known Activations