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

    Neuronpedia

    INDEX
    Explanations

    equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Holdings
    -0.08
     streamed
    -0.07
     Wander
    -0.07
    spiracy
    -0.07
     fueled
    -0.07
     NATIONAL
    -0.07
    ITUDE
    -0.07
    Framework
    -0.07
    Credits
    -0.07
     fungi
    -0.07
    POSITIVE LOGITS
     convey
    0.06
    _trampoline
    0.06
     useless
    0.06
     lubric
    0.06
     næ
    0.06
    ött
    0.06
    ivre
    0.06
    ไหน
    0.05
     úrov
    0.05
    logue
    0.05
    Act Density 0.009%

    No Known Activations