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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    baseline
    -0.07
    olg
    -0.07
     Dawson
    -0.06
    hof
    -0.06
    mann
    -0.06
    (mock
    -0.06
    bj
    -0.06
    松
    -0.06
     Reward
    -0.06
    Bone
    -0.06
    POSITIVE LOGITS
    CCR
    0.07
    _comments
    0.06
     ubytování
    0.06
     ชนะ
    0.06
     -:
    0.06
     woes
    0.06
     �
    0.06
     Det
    0.06
    ")));
↵
    0.06
     producing
    0.06
    Act Density 0.053%

    No Known Activations