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

    Neuronpedia

    INDEX
    Explanations

    now

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    asında
    -0.07
     spectro
    -0.06
    СР
    -0.06
    ircular
    -0.06
    iore
    -0.06
    carbon
    -0.06
    pesan
    -0.06
     acet
    -0.06
    chandle
    -0.06
    -neck
    -0.06
    POSITIVE LOGITS
     \
    0.07
    _directory
    0.07
     Stay
    0.07
     */
↵
    0.07
     meantime
    0.06
    론
    0.06
    icação
    0.06
     Vacation
    0.06
    ção
    0.06
     kannst
    0.06
    Act Density 0.005%

    No Known Activations