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

    Neuronpedia

    INDEX
    Explanations

    20 followed by 0

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     winch
    0.88
     amethyst
    0.85
     valleys
    0.84
     clings
    0.84
     billowing
    0.83
     driftwood
    0.83
     denser
    0.83
     thicker
    0.82
    踹
    0.82
     ridges
    0.82
    POSITIVE LOGITS
    P
    0.55
    T
    0.54
    N
    0.52
    S
    0.52
    Sh
    0.51
    app
    0.47
     University
    0.45
     Bench
    0.45
    s
    0.45
    盈利
    0.44
    Act Density 0.000%

    No Known Activations