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

    Neuronpedia

    INDEX
    Explanations

    bankruptcy, guidance, irrational

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    秥
    0.46
     doctoral
    0.44
     Zhejiang
    0.42
     மணிக்கு
    0.40
     velike
    0.39
     znajdują
    0.39
     doctorate
    0.38
     nedeniyle
    0.38
     figure
    0.38
     sensation
    0.38
    POSITIVE LOGITS
    setzung
    0.47
    palette
    0.46
    scales
    0.41
    Fin
    0.40
    patan
    0.40
    numeric
    0.40
    ína
    0.40
    Nur
    0.39
    kannten
    0.39
    फ़
    0.39
    Act Density 0.000%

    No Known Activations