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

    Neuronpedia

    INDEX
    Explanations

    choices/actions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bad
    -0.08
     Swap
    -0.07
     fifth
    -0.07
    Buttons
    -0.07
    Bad
    -0.06
     Web
    -0.06
    web
    -0.06
    ki
    -0.06
     Rod
    -0.06
    	So
    -0.06
    POSITIVE LOGITS
    ][/
    0.08
     تأثیر
    0.06
    *size
    0.06
     इतन
    0.06
    ασία
    0.06
     ．
    0.06
    ebo
    0.06
     conspic
    0.06
    �
    0.06
     caracteres
    0.06
    Act Density 0.151%

    No Known Activations