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

    Neuronpedia

    INDEX
    Explanations

    numbers in code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    τερα
    -0.07
    identity
    -0.06
    的手
    -0.06
    _reg
    -0.06
    UNT
    -0.06
    ZIP
    -0.06
    نية
    -0.06
     taky
    -0.06
    -fashion
    -0.06
    curacy
    -0.06
    POSITIVE LOGITS
     THC
    0.07
     desenv
    0.07
     blanco
    0.06
    	Json
    0.06
     [[]
    0.06
    .ToBoolean
    0.06
    大小
    0.06
     geological
    0.06
    accordion
    0.06
    "\↵
    0.06
    Act Density 0.025%

    No Known Activations