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

    Neuronpedia

    INDEX
    Explanations

    Quotation marks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tokens
    -0.06
     Druh
    -0.06
    entropy
    -0.06
    ╝
    -0.06
     कन
    -0.06
    -Trump
    -0.06
    Mes
    -0.06
    _decl
    -0.06
     orang
    -0.06
    	TEST
    -0.06
    POSITIVE LOGITS
    ASHINGTON
    0.08
     &(
    0.07
    IRCLE
    0.06
     locality
    0.06
     UserManager
    0.06
    _#{
    0.06
    ?("
    0.06
     JVM
    0.06
    lerle
    0.06
     predator
    0.06
    Act Density 0.106%

    No Known Activations