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

    Neuronpedia

    INDEX
    Explanations

    numbers followed by units or identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     crebre
    0.46
     resil
    0.44
    бы
    0.43
    ৤
    0.43
     explan
    0.43
    ⢸
    0.42
     sistemat
    0.42
     Bellingham
    0.42
     sorrows
    0.41
     presup
    0.41
    POSITIVE LOGITS
    R
    0.47
     மற்றும்
    0.46
     maupun
    0.46
    S
    0.45
    P
    0.44
    various
    0.44
     jossa
    0.43
     cui
    0.43
     अलावा
    0.39
    adi
    0.39
    Act Density 0.010%

    No Known Activations