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

    Neuronpedia

    INDEX
    Explanations

    refused

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     звичай
    -0.07
    cancelled
    -0.07
    AA
    -0.07
    Yet
    -0.07
     Ed
    -0.07
    (K
    -0.07
    Such
    -0.06
    (G
    -0.06
    ideographic
    -0.06
    є
    -0.06
    POSITIVE LOGITS
     plastic
    0.06
     Plastic
    0.06
     newspaper
    0.06
     Bollywood
    0.06
     PUBLIC
    0.06
     palavra
    0.06
    INSTALL
    0.06
     Implements
    0.06
    neck
    0.06
    "?↵↵
    0.06
    Act Density 0.018%

    No Known Activations