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

    Neuronpedia

    INDEX
    Explanations

    �

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    quine
    -0.07
     segment
    -0.07
    (package
    -0.07
     perhaps
    -0.06
     unless
    -0.06
    _elim
    -0.06
     _______,
    -0.06
    .decorate
    -0.06
    :]
    -0.06
    _reference
    -0.06
    POSITIVE LOGITS
    �
    0.21
     SOP
    0.10
     Hitch
    0.07
     Entre
    0.06
    �
    0.06
     CallingConvention
    0.06
    Laugh
    0.06
     Scre
    0.06
    -May
    0.06
    SUPER
    0.06
    Act Density 0.003%

    No Known Activations