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

    Neuronpedia

    INDEX
    Explanations

    oh

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _wave
    -0.07
    -le
    -0.07
    レ
    -0.06
     част
    -0.06
    -di
    -0.06
    取
    -0.06
    -AA
    -0.06
     Čer
    -0.06
     कम
    -0.06
    _ms
    -0.06
    POSITIVE LOGITS
    oh
    0.38
    OH
    0.23
    Oh
    0.10
     OH
    0.10
     oh
    0.10
     Roh
    0.09
    "Oh
    0.08
     noh
    0.08
     Oh
    0.07
    “Oh
    0.07
    Act Density 0.004%

    No Known Activations