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

    Neuronpedia

    INDEX
    Explanations

    von

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     нав
    -0.07
     efect
    -0.07
     increment
    -0.06
    )::
    -0.06
    cc
    -0.06
     nut
    -0.06
     respecto
    -0.06
     stavu
    -0.06
     obsessive
    -0.06
    찬
    -0.06
    POSITIVE LOGITS
     Teil
    0.16
     Disneyland
    0.08
    <j
    0.07
     बन
    0.07
     lottery
    0.06
     년
    0.06
     Lottery
    0.06
    ettel
    0.06
     Consultants
    0.06
    ROUTE
    0.06
    Act Density 0.003%

    No Known Activations