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

    Neuronpedia

    INDEX
    Explanations

    JSON field names: id, name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    س
    0.63
    璺
    0.57
    疠
    0.56
    衽
    0.54
     relapse
    0.53
     magasin
    0.52
    鐏
    0.52
     jamming
    0.52
     보호
    0.52
    ⱼ
    0.52
    POSITIVE LOGITS
    u
    0.89
    ↵↵
    0.62
    P
    0.56
    ↵↵↵↵
    0.56
    oloji
    0.55
    ar
    0.55
    ות
    0.54
     capire
    0.54
     красивые
    0.53
    Ă
    0.53
    Act Density 0.001%

    No Known Activations