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

    Neuronpedia

    INDEX
    Explanations

    helpful assistant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lly
    1.29
    hā
    1.28
    র
    1.23
    しっかり
    1.21
    orsement
    1.18
    fprintf
    1.16
    ים
    1.14
    นี่
    1.14
     Senate
    1.13
     هذا
    1.12
    POSITIVE LOGITS
     magn
    1.39
     cualidades
    1.39
    ोन
    1.30
     pontos
    1.29
     solic
    1.28
     maneira
    1.27
     maneras
    1.27
     रिश्ता
    1.25
    }">
    1.21
     дорога
    1.19
    Act Density 0.000%

    No Known Activations