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

    Neuronpedia

    INDEX
    Explanations

    free entertainmenthuman behavior

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Stunning
    0.50
    但
    0.50
     Consultant
    0.46
     but
    0.46
    but
    0.44
     ব্যবসা
    0.43
     Also
    0.43
     BUT
    0.43
     Panoramic
    0.42
    আমাদের
    0.42
    POSITIVE LOGITS
     malignancies
    0.48
     peculi
    0.47
     neoplasms
    0.46
     malignancy
    0.46
    RatingDiff
    0.45
     deprec
    0.45
     testis
    0.44
     tumorigen
    0.43
     sentencing
    0.43
     backstory
    0.43
    Act Density 0.001%

    No Known Activations