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

    Neuronpedia

    INDEX
    Explanations

    Code/technical strings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _BOOT
    -0.07
    _black
    -0.07
    trx
    -0.06
     mobil
    -0.06
    ัตว
    -0.06
    `${
    -0.06
     plá
    -0.06
    ंडल
    -0.06
    haar
    -0.06
    .enum
    -0.06
    POSITIVE LOGITS
     hotspot
    0.06
     edi
    0.06
    (country
    0.06
     ipv
    0.06
    OLLOW
    0.06
     SNAP
    0.06
     endings
    0.06
    (sem
    0.06
     coercion
    0.06
    �
    0.06
    Act Density 0.001%

    No Known Activations