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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     acre
    -0.06
    Hash
    -0.06
    ٤
    -0.06
    oftware
    -0.06
    Enough
    -0.06
    تها
    -0.06
     goodbye
    -0.06
     rn
    -0.06
     recursion
    -0.06
     Honey
    -0.06
    POSITIVE LOGITS
    镇
    0.07
     Ging
    0.07
    สภ
    0.07
     Taipei
    0.07
    _Unit
    0.07
     тепло
    0.06
    .localScale
    0.06
     úprav
    0.06
    ">'+
    0.06
     마음
    0.06
    Act Density 0.174%

    No Known Activations