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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     :-
    -0.06
     substituted
    -0.06
    RIA
    -0.06
    serializer
    -0.06
     wood
    -0.06
     builtin
    -0.06
    .IsFalse
    -0.06
     jelly
    -0.06
     motherboard
    -0.06
     dog
    -0.06
    POSITIVE LOGITS
    ْع
    0.07
    кового
    0.06
    ического
    0.06
     Somerset
    0.06
    $criteria
    0.06
     составляет
    0.06
    psc
    0.06
     человека
    0.06
    _ro
    0.06
    pons
    0.06
    Act Density 0.048%

    No Known Activations