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

    Neuronpedia

    INDEX
    Explanations

    respect and calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Colombeau
    0.55
     инстру
    0.54
    ದಾರ
    0.53
     جوړونک
    0.52
    苌
    0.52
     pronotum
    0.51
     răm
    0.51
    嬂
    0.51
    篪
    0.51
    പാ
    0.50
    POSITIVE LOGITS
    ian
    0.51
    -
    0.50
    em
    0.46
    est
    0.46
     this
    0.44
     also
    0.44
    ices
    0.44
    ize
    0.44
    itiba
    0.44
    ell
    0.43
    Act Density 0.000%

    No Known Activations