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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    екс
    -0.07
     Murder
    -0.07
    том
    -0.07
    ماری
    -0.06
    _gui
    -0.06
    盟
    -0.06
     manipulate
    -0.06
     whether
    -0.06
    omb
    -0.06
     ديگر
    -0.06
    POSITIVE LOGITS
    :checked
    0.08
     عضو
    0.06
     naw
    0.06
    _INCLUDE
    0.06
    โรงเร
    0.06
     jardin
    0.06
    _FAILURE
    0.06
     βο
    0.06
    Hang
    0.06
    ibilit
    0.06
    Act Density 0.081%

    No Known Activations