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

    Neuronpedia

    INDEX
    Explanations

    elves

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    leitung
    -0.07
     "=",
    -0.07
     миним
    -0.07
     ineff
    -0.07
    螺
    -0.07
    етич
    -0.07
    wild
    -0.07
    claimer
    -0.06
    _ghost
    -0.06
    .plus
    -0.06
    POSITIVE LOGITS
     childcare
    0.06
    Sheet
    0.06
    memberOf
    0.06
     لم
    0.06
     percussion
    0.06
     //-
    0.06
    ToAdd
    0.06
     छ
    0.06
    `↵↵
    0.06
     благод
    0.06
    Act Density 0.008%

    No Known Activations