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

    Neuronpedia

    INDEX
    Explanations

    ICD-10 codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Condition
    0.43
     UNI
    0.43
     vorbere
    0.43
     MATHEMAT
    0.43
     pdf
    0.41
     Scooter
    0.41
     PDF
    0.41
     aplik
    0.41
     ROB
    0.41
     segunda
    0.40
    POSITIVE LOGITS
     عشر
    0.39
    hees
    0.38
    udas
    0.38
    reif
    0.37
    ammad
    0.36
    segments
    0.34
    lengths
    0.34
    maxLength
    0.34
     Heel
    0.34
    heel
    0.34
    Act Density 0.002%

    No Known Activations