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

    Neuronpedia

    INDEX
    Explanations

    numbers and references

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _SELF
    -0.07
     Papua
    -0.07
    ına
    -0.07
    _dual
    -0.06
    Auto
    -0.06
    hetics
    -0.06
    -space
    -0.06
     PHYS
    -0.06
    region
    -0.06
     rx
    -0.06
    POSITIVE LOGITS
    .ResponseWriter
    0.06
     موضوع
    0.06
     Pang
    0.06
    .setAlignment
    0.06
    λης
    0.06
     sweating
    0.06
    Υ
    0.06
    �
    0.06
     precisa
    0.06
    //************************************************************************
    0.06
    Act Density 0.032%

    No Known Activations