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

    Neuronpedia

    INDEX
    Explanations

    groceries up, unpause, a valuable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    verse
    0.39
    稿
    0.39
    蠱
    0.38
    플레이
    0.38
     Verde
    0.37
    zze
    0.37
    ificar
    0.36
    啡
    0.36
    žete
    0.36
    viridis
    0.36
    POSITIVE LOGITS
     യൂണി
    0.39
    𝟐
    0.39
     migli
    0.38
     लिमिट
    0.38
    ParamList
    0.38
     indexBuffer
    0.37
     ENGLISH
    0.37
    DropDownStyle
    0.36
    രിയാ
    0.36
     matchList
    0.35
    Act Density 0.000%

    No Known Activations