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

    Neuronpedia

    INDEX
    Explanations

    story, quests, places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     immunore
    0.48
     けれど
    0.43
    🧤
    0.43
    (~
    0.41
     austenitic
    0.41
     cyclohexane
    0.41
    (""
    0.40
     いたし
    0.40
    ymethyl
    0.40
     anise
    0.40
    POSITIVE LOGITS
     K
    0.45
     Netherlands
    0.40
     Nom
    0.40
    Wish
    0.40
    Class
    0.39
     luxury
    0.39
     К
    0.39
     Class
    0.39
     Gas
    0.39
     Sharp
    0.38
    Act Density 0.000%

    No Known Activations