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

    Neuronpedia

    INDEX
    Explanations

    Strengths, nucleus, premise, desire, phenotype

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    版本的
    0.80
    utional
    0.75
    aternal
    0.69
    cheduled
    0.68
    sonian
    0.67
    abilistic
    0.66
    allist
    0.66
     hero
    0.66
    项目的
    0.65
    apolitan
    0.65
    POSITIVE LOGITS
    ος
    0.83
    ලය
    0.70
    స్సు
    0.70
    ிகு
    0.69
    தம்
    0.69
    නය
    0.69
    వులు
    0.66
    etus
    0.66
    തം
    0.66
    గం
    0.65
    Act Density 0.140%

    No Known Activations