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

    Neuronpedia

    INDEX
    Explanations

    wondering or analyzing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     안녕하세요
    0.80
    ጡ
    0.79
     erklärt
    0.79
     Thông
    0.79
     പ്രദ
    0.77
    Identifier
    0.76
     উত্তীর্ণ
    0.76
    seeker
    0.76
     Explained
    0.75
    Explained
    0.75
    POSITIVE LOGITS
     wonder
    1.98
     imagining
    1.83
     imagine
    1.83
     wondering
    1.82
     wondered
    1.81
    wonder
    1.81
     imagined
    1.72
     imagines
    1.70
     Wonder
    1.69
     fantas
    1.64
    Act Density 0.492%

    No Known Activations