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

    Neuronpedia

    INDEX
    Explanations

    FIND followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ISER
    0.50
    IN
    0.48
    ES
    0.46
    ਕ
    0.46
    Wells
    0.45
    di
    0.44
    e
    0.42
    膳
    0.42
    Well
    0.42
    的热
    0.42
    POSITIVE LOGITS
     Bento
    0.52
     crayon
    0.50
     turtleneck
    0.50
     প্রস্তুতি
    0.50
    ુ
    0.49
     microwave
    0.49
     Teenage
    0.49
     radiance
    0.49
     noroeste
    0.49
     Whyte
    0.48
    Act Density 0.000%

    No Known Activations