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

    Neuronpedia

    INDEX
    Explanations

    glass fiber

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ujących
    0.40
    Refund
    0.38
     bieten
    0.38
     ambulance
    0.37
    হিত
    0.36
    DEPEND
    0.36
    गेन
    0.36
    arii
    0.36
    ナム
    0.36
    وكب
    0.35
    POSITIVE LOGITS
     temperate
    0.49
    следова
    0.40
    slo
    0.39
     temperament
    0.38
     filled
    0.38
     sloppy
    0.37
     வைர
    0.36
     tempered
    0.35
    лизова
    0.35
    σε
    0.35
    Act Density 0.000%

    No Known Activations