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

    Neuronpedia

    INDEX
    Explanations

    blueprint construction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    newParameter
    0.43
    امر
    0.41
     disgrace
    0.39
    дации
    0.38
    ഌ
    0.38
     disgraced
    0.38
    惻
    0.38
     ruining
    0.37
    amplitude
    0.37
     पूर्वक
    0.37
    POSITIVE LOGITS
    ෙ
    0.41
     blueprints
    0.40
    asta
    0.39
    Blueprint
    0.39
    建設
    0.38
     blueprint
    0.36
    abla
    0.36
    ši
    0.36
     construction
    0.36
    ginas
    0.36
    Act Density 0.000%

    No Known Activations