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

    Neuronpedia

    INDEX
    Explanations

    variable like size

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    મેન્ટ
    0.47
     ?”
    0.46
     …”
    0.45
    叐
    0.45
    𝐨
    0.45
     zum
    0.44
     válida
    0.44
    낌
    0.44
    bole
    0.43
     получается
    0.42
    POSITIVE LOGITS
     readable
    0.42
     intelligible
    0.42
     adipose
    0.41
     peroxidase
    0.41
     classpath
    0.41
     understood
    0.40
     혹은
    0.40
     survival
    0.40
     legible
    0.40
     ඉතා
    0.40
    Act Density 0.002%

    No Known Activations