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

    Neuronpedia

    INDEX
    Explanations

    Y

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lw
    -0.07
    ForResource
    -0.07
     fury
    -0.07
     Nunes
    -0.06
    gregated
    -0.06
    43
    -0.06
     serpent
    -0.06
     tắc
    -0.06
    .Since
    -0.06
    --
    -0.06
    POSITIVE LOGITS
    .setState
    0.07
     yêu
    0.07
    çak
    0.06
     поск
    0.06
    AFF
    0.06
    っ�
    0.06
     땅
    0.06
     Everybody
    0.06
    reff
    0.06
    ênh
    0.06
    Act Density 0.010%

    No Known Activations