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

    Neuronpedia

    INDEX
    Explanations

    descriptive adjectives and nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     IUE
    0.39
    吐
    0.37
     vd
    0.37
    ヒ
    0.37
     DSP
    0.36
    DSP
    0.35
    php
    0.35
    CEED
    0.35
     Cork
    0.34
    DUP
    0.34
    POSITIVE LOGITS
     pasando
    0.46
     बराबर
    0.41
     passing
    0.40
    illez
    0.40
     obrigado
    0.40
    仴
    0.40
     істо
    0.40
    ieck
    0.40
     resemblance
    0.40
     Футбол
    0.39
    Act Density 0.001%

    No Known Activations