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

    Neuronpedia

    INDEX
    Explanations

    commands and scripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ganancias
    0.37
    勖
    0.37
    ɮ
    0.37
    为您
    0.36
    порт
    0.36
     podat
    0.36
     DDoS
    0.36
     sopa
    0.36
     tách
    0.35
    బ్ద
    0.35
    POSITIVE LOGITS
    ↵↵
    0.53
    olics
    0.41
    ↵
    0.40
    ↵↵↵
    0.37
    imidazol
    0.37
     Prevalence
    0.36
     Following
    0.35
    following
    0.34
    second
    0.34
     Olympian
    0.34
    Act Density 0.000%

    No Known Activations