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

    Neuronpedia

    INDEX
    Explanations

    contrasting magnitudes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GF
    -0.07
    WAR
    -0.07
    stoff
    -0.07
    _JUMP
    -0.07
    -Mar
    -0.07
     formulate
    -0.07
    镁
    -0.06
    ạng
    -0.06
    <>
    -0.06
    sep
    -0.06
    POSITIVE LOGITS
     substitute
    0.08
    �
    0.07
    祁
    0.07
     pestic
    0.07
     María
    0.07
    经验丰富
    0.07
     túi
    0.07
     Ruby
    0.06
    ={`
    0.06
    .isLoggedIn
    0.06
    Act Density 0.032%

    No Known Activations