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

    Neuronpedia

    INDEX
    Explanations

    depleting ozone layer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DATUM
    0.39
    𝑎
    0.38
    𝟎
    0.38
     frmt
    0.38
    โค
    0.37
    astype
    0.37
     idiosync
    0.37
     introvert
    0.37
     OU
    0.36
     لمن
    0.36
    POSITIVE LOGITS
    setStatus
    0.40
    ಟಿ
    0.39
    එ
    0.39
    Keeping
    0.38
    कहीं
    0.37
     कहीं
    0.36
    bani
    0.36
    Shark
    0.36
    ków
    0.35
    𒂍
    0.35
    Act Density 0.000%

    No Known Activations