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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    olate
    -0.07
     kapsamında
    -0.07
     Riders
    -0.06
    (dy
    -0.06
     mediated
    -0.06
     опис
    -0.06
    ided
    -0.06
     で
    -0.06
    amb
    -0.06
    -app
    -0.06
    POSITIVE LOGITS
    _lengths
    0.07
    strings
    0.07
     logger
    0.06
    懂
    0.06
    ULLET
    0.06
     Rugby
    0.06
    porto
    0.06
    主要
    0.06
    صح
    0.06
    Rib
    0.06
    Act Density 0.000%

    No Known Activations