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

    Neuronpedia

    INDEX
    Explanations

    abstract concepts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Res
    0.61
    Thumb
    0.61
    Five
    0.61
    thumb
    0.59
    Do
    0.59
    Branch
    0.57
    Assert
    0.55
    Goss
    0.55
    Fe
    0.55
    assert
    0.55
    POSITIVE LOGITS
     Wrangler
    0.71
     Verizon
    0.70
     गड़ब
    0.70
     JPMorgan
    0.70
     путем
    0.67
     KTM
    0.66
     kennen
    0.66
     számára
    0.66
     спустя
    0.66
     Kaspersky
    0.66
    Act Density 0.000%

    No Known Activations