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

    Neuronpedia

    INDEX
    Explanations

    acts of kindness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ngành
    -0.07
    س
    -0.06
    culture
    -0.06
    ۱۳۹
    -0.06
    (logits
    -0.06
    rollo
    -0.06
     prop
    -0.06
    ipc
    -0.06
    _tolerance
    -0.06
    acht
    -0.06
    POSITIVE LOGITS
     спад
    0.06
     mutated
    0.06
    .stats
    0.06
     surpass
    0.06
     fix
    0.06
     listening
    0.06
     Term
    0.06
     idiots
    0.06
    //
↵
    0.06
     Ferm
    0.06
    Act Density 0.067%

    No Known Activations