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

    Neuronpedia

    INDEX
    Explanations

    generate command

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ສາມາດ
    0.64
     sweetly
    0.55
     или
    0.55
    ພັນ
    0.53
    ລິ
    0.53
     футбол
    0.52
     respectivos
    0.52
    醤
    0.52
     ನಂತರ
    0.51
     Фургала
    0.51
    POSITIVE LOGITS
    p
    0.60
    1
    0.59
    3
    0.58
    ty
    0.55
    c
    0.55
    tr
    0.54
    ol
    0.52
    akir
    0.51
    way
    0.50
    2
    0.50
    Act Density 0.000%

    No Known Activations