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

    Neuronpedia

    INDEX
    Explanations

    specific entities, AI, and brands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fyz
    0.68
     einzel
    0.68
     singolo
    0.66
    simpl
    0.65
     gross
    0.65
     isotopes
    0.65
    abstraction
    0.64
     autoestima
    0.64
    gross
    0.64
    arbit
    0.63
    POSITIVE LOGITS
     purely
    1.11
     decidedly
    1.02
     predominantly
    1.01
     exclusively
    0.98
     distinctly
    0.96
     преимущественно
    0.93
     bersifat
    0.86
     Marxist
    0.84
     patriotic
    0.84
     explicitly
    0.83
    Act Density 0.948%

    No Known Activations