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

    Neuronpedia

    INDEX
    Explanations

    ente

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    מש
    -0.08
     positively
    -0.08
     following
    -0.08
     sis
    -0.08
     меди
    -0.07
     dumped
    -0.07
     consequence
    -0.07
     дв
    -0.07
     warmly
    -0.07
    /the
    -0.07
    POSITIVE LOGITS
     perennial
    0.09
    iksi
    0.09
    ’ess
    0.09
     dehydration
    0.08
     eterno
    0.08
    -cl
    0.07
    ’expérience
    0.07
     pencils
    0.07
    _pressure
    0.07
     Finish
    0.07
    Act Density 0.001%

    No Known Activations