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

    Neuronpedia

    INDEX
    Explanations

    research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    VERY
    -0.07
     with
    -0.07
     WITH
    -0.07
     accred
    -0.07
    	for
    -0.07
     With
    -0.07
    Internet
    -0.06
    يين
    -0.06
    olian
    -0.06
    mh
    -0.06
    POSITIVE LOGITS
    连接
    0.06
    ・マ
    0.06
    -generated
    0.05
    �
    0.05
     awarded
    0.05
    moving
    0.05
    _brightness
    0.05
    ow
    0.05
    Git
    0.05
     pseud
    0.05
    Act Density 0.128%

    No Known Activations