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

    Neuronpedia

    INDEX
    Explanations

    biological, computer, and physics terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Kanye
    0.44
     abode
    0.43
     cabling
    0.43
     OCE
    0.42
    Shard
    0.42
    Team
    0.42
     Kano
    0.42
     Team
    0.41
    Jimbo
    0.41
    CAB
    0.41
    POSITIVE LOGITS
    ára
    0.54
    yn
    0.51
    StructOf
    0.50
    uas
    0.50
    ain
    0.49
    atos
    0.49
     renfer
    0.49
    iju
    0.48
    uum
    0.48
    umm
    0.46
    Act Density 0.002%

    No Known Activations