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

    Neuronpedia

    INDEX
    Explanations

    jealous boyfriend or shepherd

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ➔
    2.55
    𝐬
    2.05
    Ɛ
    1.98
    dna
    1.98
    laws
    1.98
     petitions
    1.96
    依据
    1.95
     глаза
    1.93
    ted
    1.90
     chromosomes
    1.86
    POSITIVE LOGITS
     generality
    2.15
    да
    1.75
    جراء
    1.64
     concomit
    1.63
     industriales
    1.60
    漑
    1.59
    ö
    1.59
    溏
    1.57
    u
    1.54
    יר
    1.53
    Act Density 0.001%

    No Known Activations