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

    Neuronpedia

    INDEX
    Explanations

    not just ... also

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ahati
    1.19
    erte
    1.18
    elem
    1.17
     Analyses
    1.16
    dana
    1.15
    ंच्या
    1.13
    Untitled
    1.13
    differ
    1.11
    ﺩ
    1.10
    gay
    1.09
    POSITIVE LOGITS
    ک
    1.66
    ج
    1.59
    น
    1.44
    ก
    1.39
    。“
    1.35
    ຜະລ
    1.30
    чала
    1.27
    ન
    1.26
    យៈ
    1.25
    อง
    1.20
    Act Density 0.007%

    No Known Activations