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

    Neuronpedia

    INDEX
    Explanations

    enumeration, each, respectively

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    性和
    0.42
    度和
    0.40
    Another
    0.40
    Fl
    0.39
    other
    0.38
    Other
    0.37
    Sh
    0.36
     പല
    0.36
    Benzyloxy
    0.35
    Aud
    0.35
    POSITIVE LOGITS
     respectively
    0.86
    それぞれ
    0.72
     alike
    0.71
     respectivamente
    0.69
     각각
    0.68
     ஆகியோர்
    0.67
     എന്നിവ
    0.65
     ஆகிய
    0.64
     모두
    0.63
     တို့
    0.62
    Act Density 1.679%

    No Known Activations