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

    Neuronpedia

    INDEX
    Explanations

    terms and procedure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pubescens
    0.40
    tfrac
    0.38
    inerja
    0.38
    డని
    0.37
     Borrower
    0.36
    op
    0.36
     gluc
    0.36
    gluc
    0.36
     मधुमेह
    0.36
     flagship
    0.36
    POSITIVE LOGITS
    采访
    0.41
    记者
    0.40
    汢
    0.39
     ብ
    0.38
    ཐ
    0.38
    氛围
    0.37
    🎤
    0.37
    要求
    0.37
     চ্যালেঞ্জ
    0.37
     প্রদান
    0.37
    Act Density 0.000%

    No Known Activations