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

    Neuronpedia

    INDEX
    Explanations

    rough estimates or rules of thumb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Many
    0.42
    most
    0.40
     ب
    0.39
    Most
    0.38
    <0x99>
    0.37
    ơi
    0.37
     inval
    0.36
    Contrast
    0.36
     most
    0.36
    sc
    0.35
    POSITIVE LOGITS
     rough
    0.75
     Rough
    0.67
     Rule
    0.65
    rough
    0.63
    粗
    0.63
     approximated
    0.60
    近似
    0.59
    Rough
    0.57
     approximations
    0.57
    Rule
    0.57
    Act Density 0.000%

    No Known Activations