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

    Neuronpedia

    INDEX
    Explanations

    components and specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     absolutamente
    0.38
     başta
    0.37
     Happens
    0.36
     sowohl
    0.35
    がありますが
    0.35
     złoż
    0.35
     justices
    0.35
     jederzeit
    0.34
    はもちろん
    0.34
     pinMode
    0.33
    POSITIVE LOGITS
    8
    0.50
    using
    0.45
     via
    0.44
    via
    0.44
    ate
    0.43
    by
    0.43
    4
    0.43
    through
    0.43
    7
    0.43
    als
    0.42
    Act Density 0.074%

    No Known Activations