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

    Neuronpedia

    INDEX
    Explanations

    email addresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    面的
    0.39
    burned
    0.37
    ższy
    0.36
     числен
    0.36
     کرن
    0.36
    の
    0.36
     の
    0.36
    의
    0.36
    longitude
    0.35
    হতের
    0.35
    POSITIVE LOGITS
     info
    0.80
     INFO
    0.78
     Info
    0.73
    info
    0.67
    Info
    0.66
    INFO
    0.64
     admissions
    0.56
    submissions
    0.54
    getInfo
    0.52
     hello
    0.50
    Act Density 0.017%

    No Known Activations