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

    Neuronpedia

    INDEX
    Explanations

    emotional investment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    와의
    0.87
    પા
    0.86
    Affected
    0.82
    fulness
    0.81
     morally
    0.80
    YNAM
    0.79
    Ე
    0.79
    initial
    0.79
    existing
    0.78
    γμα
    0.77
    POSITIVE LOGITS
    ity
    1.68
    ized
    1.53
    iteit
    1.43
    ities
    1.41
    idade
    1.38
    idad
    1.35
    ITY
    1.35
    ität
    1.32
    izing
    1.28
    ité
    1.22
    Act Density 0.943%

    No Known Activations