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

    Neuronpedia

    INDEX
    Explanations

    cleverness or intelligence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     такого
    -0.08
    sexual
    -0.08
     monument
    -0.07
     replay
    -0.07
     predominantly
    -0.07
    (self
    -0.07
    [section
    -0.07
    евые
    -0.07
     nale
    -0.06
    *(-
    -0.06
    POSITIVE LOGITS
    بیر
    0.06
     straw
    0.06
    �
    0.06
     compel
    0.06
    既
    0.06
     poison
    0.06
    rvine
    0.06
     �
    0.06
    Ü
    0.06
    .telegram
    0.06
    Act Density 0.012%

    No Known Activations