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

    Neuronpedia

    INDEX
    Explanations

    Flights

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Có
    -0.07
    _nc
    -0.06
    amoto
    -0.06
    ान
    -0.06
    older
    -0.06
     presence
    -0.06
    032
    -0.06
    grim
    -0.06
    ỗ
    -0.06
     других
    -0.06
    POSITIVE LOGITS
    .JsonProperty
    0.07
    _pickle
    0.06
    _di
    0.06
     appended
    0.06
     showcased
    0.06
    _Save
    0.06
     взгляд
    0.06
    epochs
    0.06
    _zip
    0.06
    .process
    0.06
    Act Density 0.007%

    No Known Activations