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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iqu
    -0.07
     Folk
    -0.07
    rop
    -0.07
    ioxide
    -0.07
     Unicorn
    -0.07
    售
    -0.07
    anj
    -0.06
    滑
    -0.06
     olmam
    -0.06
     Share
    -0.06
    POSITIVE LOGITS
     marginBottom
    0.06
     unfair
    0.06
     ти
    0.06
     accustomed
    0.06
    .!
    0.06
     Southeast
    0.06
    Facing
    0.06
    -session
    0.06
    /create
    0.06
     dst
    0.06
    Act Density 0.009%

    No Known Activations