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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _typeDefinition
    -0.07
    ♔
    -0.07
    Commit
    -0.07
     MM
    -0.07
    箐
    -0.07
    bie
    -0.07
     SR
    -0.07
    Cog
    -0.07
    óst
    -0.07
     Cannon
    -0.06
    POSITIVE LOGITS
     venture
    0.08
    骰
    0.08
     vibrations
    0.07
    党的十九
    0.07
    市值
    0.07
    睁
    0.07
    踩
    0.07
    用工
    0.07
     expansions
    0.07
     pursuit
    0.07
    Act Density 0.002%

    No Known Activations