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

    Neuronpedia

    INDEX
    Explanations

    specific solutions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dlj
    0.57
    dziel
    0.52
    dert
    0.49
     undermining
    0.49
     compromising
    0.48
    dies
    0.45
     automation
    0.44
    dio
    0.44
    젤
    0.44
    櫒
    0.43
    POSITIVE LOGITS
    теше
    0.47
    ag
    0.47
     পর্বে
    0.47
     DOUBLE
    0.47
    p
    0.46
    ț
    0.45
    Gone
    0.45
    ۴
    0.45
    FLOAT
    0.44
     Нача
    0.44
    Act Density 0.000%

    No Known Activations