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

    Neuronpedia

    INDEX
    Explanations

    code and technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     вход
    -0.07
    .getEntity
    -0.06
    (Utils
    -0.06
     Expert
    -0.06
     Means
    -0.06
    .organ
    -0.06
     Brussels
    -0.06
    eree
    -0.06
     Damascus
    -0.06
     Twice
    -0.06
    POSITIVE LOGITS
     Sensors
    0.08
    icone
    0.07
     green
    0.07
    �
    0.07
    ários
    0.06
    ousel
    0.06
    icaret
    0.06
    ếu
    0.06
    ิม
    0.06
    caa
    0.06
    Act Density 0.000%

    No Known Activations