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

    Neuronpedia

    INDEX
    Explanations

    plus signs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ovation
    -0.08
     për
    -0.07
    my
    -0.07
    降到
    -0.07
    の中に
    -0.07
    icter
    -0.06
    hound
    -0.06
     необходимости
    -0.06
    	logrus
    -0.06
    小吃
    -0.06
    POSITIVE LOGITS
     inversion
    0.08
    (metadata
    0.07
    ///↵
    0.07
    不锈钢
    0.07
     rw
    0.07
    (ui
    0.07
    panel
    0.07
    流
    0.06
    ⋆
    0.06
    url
    0.06
    Act Density 0.001%

    No Known Activations