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

    Neuronpedia

    INDEX
    Explanations

    string

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ISTRIBUT
    -0.07
     sinks
    -0.06
    >f
    -0.06
     getWidth
    -0.06
     Folding
    -0.06
     лог
    -0.06
     گی
    -0.06
     bedside
    -0.06
    565
    -0.06
    _SIM
    -0.06
    POSITIVE LOGITS
     conditioner
    0.07
     ipsum
    0.07
    -vs
    0.06
     diệt
    0.06
     exiting
    0.06
     Marie
    0.06
     Confidence
    0.06
     mse
    0.06
    		↵	↵
    0.06
    Muslim
    0.06
    Act Density 0.013%

    No Known Activations