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

    Neuronpedia

    INDEX
    Explanations

    define capacity or target

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     torsion
    0.56
     Tor
    0.52
     tors
    0.52
     tor
    0.49
    tors
    0.47
    TOR
    0.46
     according
    0.45
     TOR
    0.45
     Tore
    0.43
     Ell
    0.43
    POSITIVE LOGITS
    Omega
    0.52
     Omega
    0.52
     Ω
    0.49
     Л
    0.48
     omega
    0.46
    omn
    0.44
     Omn
    0.44
    Omn
    0.44
    Ω
    0.43
     Omicron
    0.43
    Act Density 0.001%

    No Known Activations