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

    Neuronpedia

    INDEX
    Explanations

    US or alternatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setOn
    0.47
    iseur
    0.46
    latego
    0.45
     Вер
    0.44
    awake
    0.43
    agnetic
    0.43
    prend
    0.43
    yester
    0.43
    SendData
    0.43
    mere
    0.43
    POSITIVE LOGITS
     cel
    0.42
     alternatives
    0.41
    禧
    0.41
     reass
    0.40
     broker
    0.40
    詩
    0.39
     iris
    0.39
    翡
    0.38
     Diamond
    0.38
     perl
    0.38
    Act Density 0.000%

    No Known Activations