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

    Neuronpedia

    INDEX
    Explanations

    Possessive pronouns and "of"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -la
    -0.06
    	goto
    -0.06
    expanded
    -0.06
    ячи
    -0.06
    precated
    -0.06
    '↵↵
    -0.06
    пол
    -0.06
    =max
    -0.06
     per
    -0.06
    pk
    -0.05
    POSITIVE LOGITS
    ограф
    0.07
     تج
    0.07
    케이
    0.07
     잠
    0.07
     ступ
    0.06
     каче
    0.06
    们
    0.06
    onent
    0.06
     آتش
    0.06
    ayıf
    0.06
    Act Density 0.033%

    No Known Activations