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

    Neuronpedia

    INDEX
    Explanations

    forward slash

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    亞
    -0.07
    атора
    -0.07
    悪
    -0.07
    boys
    -0.07
     el
    -0.06
     pools
    -0.06
     daylight
    -0.06
     AFP
    -0.06
    оке
    -0.06
     tách
    -0.06
    POSITIVE LOGITS
     incremental
    0.07
    program
    0.06
     техні
    0.06
     Credentials
    0.06
     STYLE
    0.06
     Adolescent
    0.06
    	scale
    0.06
     จำ
    0.06
     MPC
    0.06
     Vide
    0.06
    Act Density 0.003%

    No Known Activations