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

    Neuronpedia

    INDEX
    Explanations

    makeup

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    治好
    -0.07
    导游
    -0.07
     ساع
    -0.07
     Morrow
    -0.07
    '")↵
    -0.07
    ניס
    -0.07
    .getJSONArray
    -0.07
     Misc
    -0.07
    Autoresizing
    -0.07
    Basically
    -0.07
    POSITIVE LOGITS
     בח
    0.07
    体验
    0.07
    桶
    0.07
     qa
    0.07
     па
    0.06
    BOX
    0.06
    	mat
    0.06
    question
    0.06
    pray
    0.06
    department
    0.06
    Act Density 0.001%

    No Known Activations