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

    Neuronpedia

    INDEX
    Explanations

    nuclear reactors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arg
    -0.08
    antes
    -0.07
    /Form
    -0.07
     DF
    -0.07
    -time
    -0.07
     moral
    -0.07
     mutation
    -0.06
    inal
    -0.06
     Roth
    -0.06
     Gerry
    -0.06
    POSITIVE LOGITS
     củ
    0.06
    เคล
    0.06
    Throughout
    0.06
    Serialize
    0.06
     ineffective
    0.06
    Contact
    0.06
     становить
    0.06
     nike
    0.06
     tirelessly
    0.06
    ervations
    0.06
    Act Density 0.025%

    No Known Activations