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

    Neuronpedia

    INDEX
    Explanations

    brazilian, fizzy, buzzy, ozone, wazuh

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    erà
    0.40
    ⚈
    0.39
    רט
    0.38
    zadeh
    0.38
    циях
    0.38
    ffler
    0.38
    रेशन
    0.37
    수록
    0.37
    atten
    0.37
     Barang
    0.37
    POSITIVE LOGITS
    ়
    0.93
    нодоро
    0.76
    zy
    0.67
    ्ड
    0.65
    ookeeper
    0.63
    ürich
    0.60
    wyczaj
    0.57
    ombies
    0.57
    epam
    0.56
    quierda
    0.56
    Act Density 0.094%

    No Known Activations