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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Twitter
    -0.07
     Numbers
    -0.06
     Saudi
    -0.06
     Indonesia
    -0.06
     Heroes
    -0.06
     jquery
    -0.06
     Came
    -0.06
    нав
    -0.06
     části
    -0.06
    \API
    -0.06
    POSITIVE LOGITS
    _LOAD
    0.07
    ToString
    0.07
    egasus
    0.07
     ترب
    0.07
    consider
    0.07
    ENCED
    0.07
    _concat
    0.06
    plib
    0.06
    _PROD
    0.06
     trval
    0.06
    Act Density 0.021%

    No Known Activations