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

    Neuronpedia

    INDEX
    Explanations

    documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Mutable
    -0.07
     상
    -0.07
     dato
    -0.07
    �
    -0.07
     pady
    -0.06
    vector
    -0.06
    _even
    -0.06
    เ
    -0.06
     Кри
    -0.06
    ül
    -0.06
    POSITIVE LOGITS
    	connect
    0.07
     deduct
    0.06
     freezes
    0.06
    	render
    0.06
     breaches
    0.06
     reward
    0.06
    ΙΟΥ
    0.06
     bonus
    0.06
     sexism
    0.06
    Action
    0.06
    Act Density 0.000%

    No Known Activations