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

    Neuronpedia

    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     consulted
    -0.06
     Weekend
    -0.06
    .external
    -0.06
    pent
    -0.06
    -ton
    -0.06
    termin
    -0.06
     Thinking
    -0.06
    lid
    -0.06
     качестве
    -0.06
    .getcwd
    -0.06
    POSITIVE LOGITS
    Sym
    0.07
     likelihood
    0.07
     bulbs
    0.07
     располож
    0.06
    uniform
    0.06
    +=(
    0.06
     ){↵↵
    0.06
    Exchange
    0.06
     massa
    0.06
     takım
    0.06
    Act Density 0.018%

    No Known Activations