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

    Neuronpedia

    INDEX
    Explanations

    basic business border

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     confound
    0.39
    issaient
    0.38
     dynasty
    0.37
     monospace
    0.37
    ოვანი
    0.36
     confounded
    0.36
     সর্বনাশ
    0.36
    baarheid
    0.36
    isotropic
    0.35
    roff
    0.35
    POSITIVE LOGITS
     Et
    0.42
    Patch
    0.39
     दौड़
    0.39
     ។
    0.39
     RÉ
    0.39
    pä
    0.39
     Pol
    0.38
    Sampler
    0.38
    مس
    0.38
     Sam
    0.38
    Act Density 0.000%

    No Known Activations