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

    Neuronpedia

    INDEX
    Explanations

    insurance risk categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zeichnung
    0.71
     adapters
    0.69
     primitive
    0.68
     cylind
    0.68
     primit
    0.65
    やはり
    0.64
     champignons
    0.64
     "[
    0.63
     pictogram
    0.62
     agglut
    0.62
    POSITIVE LOGITS
    8
    0.85
    1
    0.82
    5
    0.75
    9
    0.75
    3
    0.73
     Với
    0.73
    6
    0.71
    2
    0.70
    7
    0.70
    4
    0.69
    Act Density 0.000%

    No Known Activations