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

    Neuronpedia

    INDEX
    Explanations

    relationship indicates likelihood

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     incredibly
    0.39
    诹
    0.39
    ง
    0.39
    aud
    0.39
    依旧
    0.38
     이미
    0.38
     inse
    0.38
    ందో
    0.38
    う
    0.38
    on
    0.37
    POSITIVE LOGITS
     widers
    0.45
     Wikiseite
    0.43
    DESCRIPTOR
    0.42
     Verbesser
    0.41
    SERVICES
    0.41
     ACHIE
    0.41
    ({});
    0.41
     což
    0.41
     बबल
    0.41
     MINISTRY
    0.41
    Act Density 0.007%

    No Known Activations