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

    Neuronpedia

    INDEX
    Explanations

    social media post

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Franks
    0.66
    威力
    0.64
     grande
    0.63
     puissant
    0.59
     diaspora
    0.58
     pro
    0.58
     power
    0.58
     chiefly
    0.58
     kiosks
    0.58
     plano
    0.57
    POSITIVE LOGITS
    🦷
    0.66
    Reduce
    0.64
     lineColorSpace
    0.64
    ”),
    0.62
     LIABILITY
    0.62
    ListComponent
    0.59
     SHEET
    0.58
    ্লো
    0.57
     ورزش
    0.57
    csname
    0.57
    Act Density 0.000%

    No Known Activations