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

    Neuronpedia

    INDEX
    Explanations

    without

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    43
    -0.07
    _bd
    -0.06
    ecs
    -0.06
    迹
    -0.06
     Cup
    -0.06
    ivi
    -0.06
     Rank
    -0.06
    _VARS
    -0.06
    }}↵↵
    -0.06
     utilize
    -0.06
    POSITIVE LOGITS
    .Bind
    0.07
     ود
    0.07
    지노
    0.06
     버
    0.06
     abundance
    0.06
    _probe
    0.06
     Usuarios
    0.06
     unable
    0.06
    ,value
    0.06
    aped
    0.06
    Act Density 0.015%

    No Known Activations