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

    Neuronpedia

    INDEX
    Explanations

    also have

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     أو
    0.82
     egyéb
    0.76
    geteilt
    0.73
     Vergleich
    0.72
    igte
    0.72
     إلا
    0.71
     hoặc
    0.69
    ັ້ງ
    0.69
     أخرى
    0.68
    或
    0.68
    POSITIVE LOGITS
    ★
    0.63
    "],
    0.63
     present
    0.63
     fear
    0.63
     Dora
    0.61
     Belg
    0.61
     Nar
    0.60
    issima
    0.60
     portraying
    0.60
    Rais
    0.59
    Act Density 0.026%

    No Known Activations