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

    Neuronpedia

    INDEX
    Explanations

    stack

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Float
    -0.07
     Sullivan
    -0.07
     isVisible
    -0.06
    PCI
    -0.06
    .isNotBlank
    -0.06
    /bash
    -0.06
    startswith
    -0.06
     것을
    -0.06
     sple
    -0.06
     وات
    -0.06
    POSITIVE LOGITS
     −
    0.07
    �
    0.06
    ｀
    0.06
     entitlement
    0.06
    �
    0.06
     brav
    0.06
    achines
    0.06
    �
    0.06
    ListBox
    0.06
    tbody
    0.06
    Act Density 0.005%

    No Known Activations