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

    Neuronpedia

    INDEX
    Explanations

    hood

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     relative
    -0.08
     respect
    -0.07
     left
    -0.07
    (path
    -0.07
    	Ext
    -0.07
     lst
    -0.06
     flexible
    -0.06
     pair
    -0.06
    安排
    -0.06
     asteroid
    -0.06
    POSITIVE LOGITS
     childhood
    0.13
     Childhood
    0.12
    niej
    0.08
    ῶ
    0.07
     Cornwall
    0.07
    ประถม
    0.07
    ufe
    0.07
     Sylvia
    0.07
     şiddet
    0.07
    áj
    0.07
    Act Density 0.005%

    No Known Activations