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

    Neuronpedia

    INDEX
    Explanations

    disbelief or surprise

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     станд
    -0.07
     Va
    -0.07
    숏
    -0.07
    anvas
    -0.07
    oor
    -0.06
    Version
    -0.06
    ogo
    -0.06
    疏
    -0.06
    telefono
    -0.06
    Campo
    -0.06
    POSITIVE LOGITS
     prune
    0.08
    trajectory
    0.08
    _correction
    0.07
    Have
    0.07
    下列
    0.07
    剿
    0.07
    borough
    0.07
     треб
    0.07
    鬏
    0.06
    立志
    0.06
    Act Density 0.046%

    No Known Activations