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

    Neuronpedia

    INDEX
    Explanations

    cup

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     transmitir
    -0.08
     learned
    -0.08
     transmitted
    -0.08
    _unpack
    -0.07
     envy
    -0.07
     tan
    -0.07
     aprender
    -0.07
    _memory
    -0.07
     subtle
    -0.07
     transmitting
    -0.07
    POSITIVE LOGITS
    慈
    0.09
    Skipping
    0.08
     compras
    0.08
     administrativo
    0.08
    �
    0.08
    כה
    0.08
     全国
    0.08
     surpresa
    0.07
     susceptibility
    0.07
     smash
    0.07
    Act Density 0.007%

    No Known Activations