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

    Neuronpedia

    INDEX
    Explanations

    subject then output

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ꮙ
    0.46
     Dạ
    0.45
     vườn
    0.44
    ⚤
    0.43
     với
    0.42
     сахар
    0.42
     mús
    0.42
     цих
    0.41
     этих
    0.41
     venge
    0.41
    POSITIVE LOGITS
    好評
    0.44
     Think
    0.42
    рун
    0.41
    pulumi
    0.40
    Think
    0.40
    playing
    0.39
     editorials
    0.39
    груп
    0.39
    print
    0.38
    reflect
    0.38
    Act Density 0.002%

    No Known Activations