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

    Neuronpedia

    INDEX
    Explanations

    Scientific descriptions of function

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    WISE
    -0.07
    shelf
    -0.07
    ############################################################
    -0.07
     blí
    -0.06
    /System
    -0.06
     lời
    -0.06
     Pharma
    -0.06
    (weight
    -0.06
     embryos
    -0.06
    arget
    -0.06
    POSITIVE LOGITS
    กร
    0.07
    _modify
    0.06
    "f
    0.06
     dominate
    0.06
     모든
    0.06
    uf
    0.06
     sl
    0.06
    Strong
    0.06
     Св
    0.06
    	cr
    0.05
    Act Density 0.015%

    No Known Activations