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

    Neuronpedia

    INDEX
    Explanations

    locations followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     brittle
    0.46
    oh
    0.38
     prosecuting
    0.38
     approval
    0.37
     brine
    0.36
     terrain
    0.36
     substituting
    0.36
     substitutions
    0.36
     खेलते
    0.36
    ió
    0.35
    POSITIVE LOGITS
     Canva
    0.51
    ব্যাপ
    0.48
     যেই
    0.46
    粿
    0.46
     Creates
    0.42
     يقول
    0.41
    mazing
    0.41
     Hib
    0.41
     unglaublich
    0.40
     Maintenant
    0.40
    Act Density 0.001%

    No Known Activations