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

    Neuronpedia

    INDEX
    Explanations

    Demonstr

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ilitary
    -0.09
    ीन
    -0.08
     დაკ
    -0.08
     testi
    -0.08
     всему
    -0.08
     экскур
    -0.08
    >manual
    -0.08
    MERCHANTABILITY
    -0.08
     workshops
    -0.08
     moesten
    -0.08
    POSITIVE LOGITS
    ably
    0.20
    able
    0.15
    ablemente
    0.12
    ables
    0.11
    ly
    0.10
    ible
    0.10
    ates
    0.10
    áveis
    0.10
    ative
    0.10
    abble
    0.09
    Act Density 0.002%

    No Known Activations