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

    Neuronpedia

    INDEX
    Explanations

    code syntax or lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     excellence
    0.75
     realism
    0.65
     retribution
    0.65
     Pokémon
    0.64
     religion
    0.61
     conic
    0.59
     apricots
    0.58
     flore
    0.58
     dreams
    0.57
     warmer
    0.57
    POSITIVE LOGITS
    Cadastro
    0.55
    Conflicts
    0.55
     라
    0.54
    Dependent
    0.53
     Terbaru
    0.53
    MDEw
    0.52
    Przyp
    0.52
    Available
    0.52
    Principal
    0.52
    ก่
    0.52
    Act Density 0.041%

    No Known Activations