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

    Neuronpedia

    INDEX
    Explanations

    id

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     хто
    -0.07
     структу
    -0.07
     mocker
    -0.07
    ové
    -0.06
     Orch
    -0.06
    

↵
    -0.06
    swap
    -0.06
    <<<<<<<<
    -0.06
    Pok
    -0.06
     pře
    -0.06
    POSITIVE LOGITS
    Id
    0.11
     Id
    0.10
    -id
    0.10
    _ID
    0.10
     ID
    0.10
     id
    0.10
    -ID
    0.09
    ID
    0.09
    .Id
    0.09
    .id
    0.09
    Act Density 0.070%

    No Known Activations