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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	j
    -0.06
    pleado
    -0.06
    .getWriter
    -0.06
     zlep
    -0.06
    crollView
    -0.06
     poner
    -0.06
    operator
    -0.06
    _INTERNAL
    -0.05
    strtolower
    -0.05
    タル
    -0.05
    POSITIVE LOGITS
    vie
    0.07
     pek
    0.06
    ש
    0.06
     Usually
    0.06
    beat
    0.06
    .AF
    0.06
     rabbit
    0.06
    reader
    0.06
    Feature
    0.06
    Age
    0.06
    Act Density 0.004%

    No Known Activations