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

    Neuronpedia

    INDEX
    Explanations

    Ant

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     counterpart
    -0.06
     probability
    -0.06
     Mid
    -0.06
    				
↵
    -0.06
     здійс
    -0.06
     dív
    -0.06
    기가
    -0.06
     finishing
    -0.06
    ексу
    -0.06
    hours
    -0.06
    POSITIVE LOGITS
     Propel
    0.07
    568
    0.07
    .setColumns
    0.06
    ERRU
    0.06
    Advertis
    0.06
    (Collections
    0.06
     embarrass
    0.06
    osen
    0.06
    URRENT
    0.06
    _OPER
    0.06
    Act Density 0.061%

    No Known Activations