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

    Neuronpedia

    INDEX
    Explanations

    personal favorites

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     resilience
    -0.07
     aerobic
    -0.07
    _Top
    -0.07
     план
    -0.07
     pwd
    -0.07
     Gamma
    -0.07
     spherical
    -0.07
    841
    -0.07
     Svět
    -0.07
     maximal
    -0.07
    POSITIVE LOGITS
    :@{
    0.07
    χε
    0.07
    �
    0.07
    _YES
    0.06
    ener
    0.06
     addItem
    0.06
     ＼:
    0.06
    elf
    0.06
     *----------------------------------------------------------------
    0.06
    ufreq
    0.06
    Act Density 0.025%

    No Known Activations