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

    Neuronpedia

    INDEX
    Explanations

    actions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dataset
    -0.06
     Crush
    -0.06
    $list
    -0.06
    .ttf
    -0.06
    abad
    -0.06
     tbody
    -0.06
    	best
    -0.06
    =utf
    -0.06
     database
    -0.06
    UCKET
    -0.06
    POSITIVE LOGITS
     actions
    0.12
    岳
    0.08
     quien
    0.07
     acciones
    0.07
     závě
    0.07
     behavior
    0.07
    令
    0.07
     Preferences
    0.07
     action
    0.07
     действия
    0.07
    Act Density 0.024%

    No Known Activations