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

    Neuronpedia

    INDEX
    Explanations

    -off

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    idas
    -0.07
    ioni
    -0.07
    持
    -0.07
    .command
    -0.07
    慮
    -0.07
    ㈰
    -0.07
    专
    -0.07
    мыш
    -0.07
    .notify
    -0.06
    _RUNTIME
    -0.06
    POSITIVE LOGITS
     нужны
    0.08
     çı
    0.07
     Ferd
    0.07
    (klass
    0.07
    村里
    0.07
     nå
    0.07
    Scripts
    0.07
    _REFERENCE
    0.07
    毯
    0.07
     sits
    0.06
    Act Density 0.284%

    No Known Activations