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
    (service
    -0.07
    /ros
    -0.07
    hattan
    -0.06
    /sources
    -0.06
     modelling
    -0.06
     Proper
    -0.06
    hpp
    -0.06
     หล
    -0.06
    ském
    -0.06
     cellar
    -0.06
    POSITIVE LOGITS
     vom
    0.07
    Universal
    0.07
     après
    0.07
    _response
    0.06
    Hibernate
    0.06
     Papa
    0.06
     babes
    0.06
    бора
    0.06
    -dd
    0.06
    Allen
    0.06
    Act Density 0.007%

    No Known Activations