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

    Neuronpedia

    INDEX
    Explanations

    PS or Psy beginnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     /\.
    0.40
    unnumbered
    0.37
    ляць
    0.37
    ponenten
    0.37
     vec
    0.36
    gebras
    0.36
     Fourteenth
    0.36
    দ্ভুত
    0.36
    gever
    0.36
    addTo
    0.36
    POSITIVE LOGITS
     ps
    1.60
     PS
    1.52
     Ps
    1.43
    PS
    1.28
     Psy
    1.23
     PSF
    1.21
    Ps
    1.20
     psy
    1.20
    ps
    1.16
     ψ
    1.16
    Act Density 0.022%

    No Known Activations