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

    Neuronpedia

    INDEX
    Explanations

    Cod

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    肪
    -0.07
    asename
    -0.07
     بل
    -0.07
     Append
    -0.07
     carne
    -0.07
     Without
    -0.07
    곀
    -0.06
    .defineProperty
    -0.06
    ◡
    -0.06
    가입
    -0.06
    POSITIVE LOGITS
    ################################################################################
    0.08
     европей
    0.08
    最关键
    0.07
    שבת
    0.07
    third
    0.07
    uggested
    0.07
    ー�
    0.07
    controls
    0.07
    (loc
    0.07
    ces
    0.07
    Act Density 0.008%

    No Known Activations