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

    Neuronpedia

    INDEX
    Explanations

    I am

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     확보
    0.81
     triggering
    0.80
    apparent
    0.80
     apparent
    0.80
    коменду
    0.77
    relevant
    0.74
    pal
    0.74
     flagging
    0.72
     seeming
    0.72
    ามารถ
    0.72
    POSITIVE LOGITS
     بودم
    1.04
     say
    0.99
     была
    0.92
     был
    0.91
     ছিলনা
    0.89
     was
    0.87
     были
    0.86
     было
    0.86
     look
    0.85
     hoje
    0.85
    Act Density 0.049%

    No Known Activations