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

    Neuronpedia

    INDEX
    Explanations

    Money and budgets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    注
    -0.07
    medium
    -0.07
    
    -0.07
    .binding
    -0.07
     갑
    -0.06
     注
    -0.06
    ital
    -0.06
    Submission
    -0.06
     obligatory
    -0.06
     economical
    -0.06
    POSITIVE LOGITS
    靠
    0.07
    lush
    0.06
    ﾑ
    0.06
    ','=',
    0.06
    _event
    0.06
    }},
    0.06
     afirm
    0.06
     mongoose
    0.06
    Jessica
    0.06
    jo
    0.06
    Act Density 0.013%

    No Known Activations