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

    Neuronpedia

    INDEX
    Explanations

    sections 721 and 351

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.55
     Вер
    0.51
    ني
    0.49
    Swan
    0.49
    Design
    0.48
     និង
    0.48
    }]$
    0.47
    电气
    0.46
    Dev
    0.45
    -
    0.44
    POSITIVE LOGITS
     renfer
    0.51
     invari
    0.46
     lacrosse
    0.45
    လေး
    0.45
     ellipso
    0.44
    "".
    0.44
     subpar
    0.44
     oval
    0.44
    specialchars
    0.44
     organizações
    0.44
    Act Density 0.004%

    No Known Activations