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

    Neuronpedia

    INDEX
    Explanations

    businesses compared, GPU)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bona
    0.41
    emoration
    0.41
    শিশ
    0.39
    goatee
    0.38
    NumberOperation
    0.37
    cote
    0.37
     школи
    0.37
    죵
    0.37
    下图
    0.37
    isms
    0.37
    POSITIVE LOGITS
     Roy
    0.42
     Form
    0.41
    oj
    0.40
     extr
    0.40
     Robins
    0.39
     Aqu
    0.38
     written
    0.37
     Fernando
    0.36
     reins
    0.36
     autom
    0.36
    Act Density 0.000%

    No Known Activations