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

    Neuronpedia

    INDEX
    Explanations

    fill in the blank

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     री
    -0.08
     Digest
    -0.08
    лыш
    -0.08
     digest
    -0.08
     Transport
    -0.07
     Deportes
    -0.07
     Luis
    -0.07
    _digest
    -0.07
    Luis
    -0.07
     Prado
    -0.07
    POSITIVE LOGITS
    shall
    0.08
    Ess
    0.07
     niches
    0.07
     fel
    0.07
    elja
    0.07
     accommodation
    0.07
    Injection
    0.07
     parametr
    0.07
     Si
    0.07
    Paper
    0.07
    Act Density 0.001%

    No Known Activations