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

    Neuronpedia

    INDEX
    Explanations

    visual detail and effects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     M
    0.61
     I
    0.59
     children
    0.57
     prenant
    0.57
     Cartesian
    0.56
     A
    0.54
     m
    0.52
     best
    0.50
     rea
    0.50
     disassembled
    0.50
    POSITIVE LOGITS
    ωση
    0.55
    iegel
    0.54
    ့်
    0.52
    та
    0.52
    rjust
    0.52
    "',
    0.50
    েস্ক
    0.49
    raits
    0.49
     PWMB
    0.49
     ลด
    0.49
    Act Density 0.478%

    No Known Activations