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

    Neuronpedia

    INDEX
    Explanations

    Sec

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     कव
    -0.07
    Rank
    -0.07
    Ros
    -0.07
    DG
    -0.07
    PASSWORD
    -0.07
    TEX
    -0.06
     exe
    -0.06
     ENC
    -0.06
    θερ
    -0.06
     Spoon
    -0.06
    POSITIVE LOGITS
     представляет
    0.07
     hopefully
    0.07
    _standard
    0.06
    -workers
    0.06
     för
    0.06
    nants
    0.06
     slashed
    0.06
    ementia
    0.06
     accomplishments
    0.06
    -files
    0.06
    Act Density 0.011%

    No Known Activations