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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     amaç
    -0.07
     світу
    -0.06
    runs
    -0.06
    _aw
    -0.06
     admire
    -0.06
     compensated
    -0.06
     Il
    -0.06
    া
    -0.06
    无法
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    .Binary
    0.07
    _func
    0.07
     FIXED
    0.07
    REDIS
    0.07
     strán
    0.06
     feelings
    0.06
     Redis
    0.06
    _FULL
    0.06
    ())),
    0.06
     července
    0.06
    Act Density 0.000%

    No Known Activations