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

    Neuronpedia

    INDEX
    Explanations

    *(

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mer
    -0.07
    _config
    -0.07
    .check
    -0.07
     Plants
    -0.07
     vegetables
    -0.07
    หล
    -0.07
     finances
    -0.07
     Europe
    -0.07
     power
    -0.07
     Mercedes
    -0.07
    POSITIVE LOGITS
     :(
    0.07
    _fake
    0.07
     *(
    0.07
     (~(
    0.07
    -AA
    0.06
     amatør
    0.06
     먼
    0.06
    (InitializedTypeInfo
    0.06
    qualification
    0.06
    *(
    0.06
    Act Density 0.044%

    No Known Activations