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

    Neuronpedia

    INDEX
    Explanations

    Code/conversation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .operator
    -0.06
     приня
    -0.06
    	head
    -0.06
     думку
    -0.06
     Morav
    -0.06
     acquitted
    -0.06
    Tester
    -0.06
     başlay
    -0.06
     Grab
    -0.06
     дела
    -0.06
    POSITIVE LOGITS
     beneath
    0.06
    /bower
    0.06
    449
    0.06
    ;amp
    0.06
    569
    0.06
    AuthGuard
    0.06
    _calendar
    0.06
    043
    0.06
    bv
    0.06
     lamb
    0.06
    Act Density 0.000%

    No Known Activations