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

    Neuronpedia

    INDEX
    Explanations

    Code and text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Like
    -0.08
    اویر
    -0.07
     Democr
    -0.07
     дальней
    -0.07
     recipes
    -0.07
    gree
    -0.07
     Pac
    -0.07
     LIKE
    -0.07
    �
    -0.06
     порів
    -0.06
    POSITIVE LOGITS
    �
    0.06
     hdc
    0.06
    .success
    0.06
     buflen
    0.06
    emodel
    0.06
    减
    0.05
     conditional
    0.05
    olution
    0.05
    ради
    0.05
     excess
    0.05
    Act Density 0.000%

    No Known Activations