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

    Neuronpedia

    INDEX
    Explanations

    giant ball

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,+\
    0.85
    ulty
    0.82
    gwood
    0.80
     кандай
    0.79
    čia
    0.79
    ξι
    0.78
    čių
    0.78
     ljudi
    0.77
    દાન
    0.77
    olome
    0.76
    POSITIVE LOGITS
     Date
    0.82
     sodass
    0.68
     which
    0.64
     date
    0.60
     Format
    0.60
     please
    0.60
     Buy
    0.59
     com
    0.59
    并在
    0.58
    Date
    0.58
    Act Density 0.001%

    No Known Activations