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

    Neuronpedia

    INDEX
    Explanations

    by Real Engineering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ോഗ്യ
    0.54
    semos
    0.53
     قانون
    0.52
    ško
    0.52
    俔
    0.51
    規則
    0.49
    jsko
    0.47
     വിശ്വാ
    0.46
    业协会
    0.46
    >∕</
    0.46
    POSITIVE LOGITS
    ↵
    0.43
    num
    0.43
    number
    0.42
    det
    0.42
     NUM
    0.42
    NUM
    0.42
    br
    0.41
    TR
    0.41
    osh
    0.41
    is
    0.41
    Act Density 0.000%

    No Known Activations