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

    Neuronpedia

    INDEX
    Explanations

    storing tensors and models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     SEQU
    0.48
     proffered
    0.47
     polynucle
    0.47
     assumptive
    0.46
     iccad
    0.46
     vườn
    0.46
     sequels
    0.45
    ultiplier
    0.43
     successors
    0.43
     embankment
    0.43
    POSITIVE LOGITS
    G
    0.53
    TB
    0.51
    U
    0.47
    SD
    0.46
    SH
    0.45
    SDS
    0.44
     TB
    0.43
    C
    0.43
    H
    0.43
    ON
    0.43
    Act Density 0.002%

    No Known Activations