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

    Neuronpedia

    INDEX
    Explanations

    scientific concepts and measures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    代表
    0.44
     Poc
    0.42
    Pool
    0.42
    yle
    0.41
     pool
    0.41
    POI
    0.41
    SI
    0.39
    pool
    0.38
     tutt
    0.38
    Mr
    0.38
    POSITIVE LOGITS
    न्नत
    0.44
     വിവ
    0.39
    VISION
    0.39
    trasound
    0.38
    డ్డు
    0.38
     ид
    0.38
    OGND
    0.37
    熊猫
    0.37
    दिनी
    0.37
    umination
    0.37
    Act Density 0.000%

    No Known Activations