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

    Neuronpedia

    INDEX
    Explanations

    Doing exercises

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ą
    -0.07
     Lost
    -0.07
    amentos
    -0.06
    .compute
    -0.06
    ilmektedir
    -0.06
    ANO
    -0.06
     об
    -0.06
     mapping
    -0.06
    染
    -0.06
     receptive
    -0.06
    POSITIVE LOGITS
    ….
    0.07
    ASP
    0.07
     erre
    0.07
    ?>"><
    0.06
    ển
    0.06
     />';↵
    0.06
    ,,
    0.06
    -hole
    0.06
    .Direct
    0.06
    :href
    0.06
    Act Density 0.018%

    No Known Activations