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

    Neuronpedia

    INDEX
    Explanations

    systemd services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     I
    1.76
     Sienna
    1.72
     A
    1.65
    də
    1.62
     Bcl
    1.54
    nA
    1.52
    lardan
    1.47
    𝘏
    1.47
    InCategory
    1.45
     Tensorflow
    1.45
    POSITIVE LOGITS
    ться
    2.19
    ação
    1.95
    ič
    1.86
    ir
    1.73
    aus
    1.70
    6
    1.66
    7
    1.66
    8
    1.64
     trabalh
    1.59
    4
    1.59
    Act Density 0.004%

    No Known Activations