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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Proposal
    -0.08
     발매
    -0.07
     KP
    -0.07
     mailing
    -0.07
     Vz
    -0.07
    Generator
    -0.07
     decking
    -0.07
    uction
    -0.07
    sampling
    -0.06
    KP
    -0.06
    POSITIVE LOGITS
     ظ
    0.08
     число
    0.07
     //$
    0.06
    										↵
    0.06
    呼
    0.06
     skewed
    0.06
     позволя
    0.06
    โม
    0.06
    ？」↵↵
    0.06
     unreliable
    0.06
    Act Density 0.001%

    No Known Activations