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

    Neuronpedia

    INDEX
    Explanations

    what is called

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }{
    0.71
     ও
    0.71
     ಹೃ
    0.68
     तमाम
    0.68
    нето
    0.68
    ഴും
    0.67
    橿
    0.66
     и
    0.66
     periódico
    0.65
    NIA
    0.64
    POSITIVE LOGITS
    "
    0.94
    t
    0.81
    ون
    0.76
    v
    0.76
    س
    0.72
     called
    0.70
    är
    0.69
    n
    0.67
    ου
    0.64
    ts
    0.63
    Act Density 0.022%

    No Known Activations