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

    Neuronpedia

    INDEX
    Explanations

    plus signs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     comenzamos
    0.51
    lyPlugin
    0.50
    स्तक
    0.49
     primaryLanguage
    0.45
    ┇
    0.45
    ޘ
    0.45
    ✷
    0.45
     iniziamo
    0.45
     acompan
    0.44
    quele
    0.44
    POSITIVE LOGITS
     financiers
    0.42
    *
    0.41
    ोट
    0.40
     standards
    0.39
    还是要
    0.38
    C
    0.37
     formal
    0.36
    Sup
    0.36
     prejudice
    0.35
    S
    0.35
    Act Density 0.001%

    No Known Activations