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

    Neuronpedia

    INDEX
    Explanations

    rdf

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _change
    -0.07
    	perror
    -0.07
     quir
    -0.07
    motion
    -0.07
    ार
    -0.06
    model
    -0.06
    _outputs
    -0.06
    court
    -0.06
    Ice
    -0.06
     kwargs
    -0.06
    POSITIVE LOGITS
     předsed
    0.08
     دریافت
    0.06
     pada
    0.06
    dik
    0.06
     FHA
    0.06
     prat
    0.06
     đề
    0.06
    .rot
    0.06
     canv
    0.06
    muz
    0.06
    Act Density 0.001%

    No Known Activations