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

    Neuronpedia

    INDEX
    Explanations

    direction and location

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Pop
    -0.08
    prenom
    -0.07
    齇
    -0.07
     immer
    -0.07
    ثور
    -0.07
     passion
    -0.07
     contemporary
    -0.07
    宾
    -0.07
    becca
    -0.07
    岁的
    -0.07
    POSITIVE LOGITS
    PATH
    0.08
     ugl
    0.07
     الغ
    0.07
    _KHR
    0.07
     ARG
    0.07
    吸附
    0.07
    	Value
    0.07
     בל
    0.07
    .label
    0.06
    קצה
    0.06
    Act Density 0.029%

    No Known Activations