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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Addr
    -0.07
     furnish
    -0.06
    -prefix
    -0.06
     países
    -0.06
     ent
    -0.06
     замі
    -0.06
     nine
    -0.06
     jak
    -0.06
    _MAKE
    -0.06
    -result
    -0.06
    POSITIVE LOGITS
    oom
    0.07
     Marl
    0.07
    unities
    0.07
     contraception
    0.06
    onis
    0.06
    likelihood
    0.06
     AssemblyTitle
    0.06
    ettel
    0.06
     Lionel
    0.06
    “It
    0.06
    Act Density 0.073%

    No Known Activations