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

    Neuronpedia

    INDEX
    Explanations

    the first

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Abu
    -0.07
    ynamodb
    -0.07
     negotiations
    -0.06
    另外
    -0.06
    進
    -0.06
    唯一
    -0.06
    ,cv
    -0.06
     frequently
    -0.06
    _HEIGHT
    -0.06
     easier
    -0.06
    POSITIVE LOGITS
    Л
    0.07
     id
    0.06
    lament
    0.06
    àng
    0.06
    ',(
    0.06
    encias
    0.06
    -ves
    0.06
    _growth
    0.06
     MP
    0.06
     ActionType
    0.06
    Act Density 0.124%

    No Known Activations