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

    Neuronpedia

    INDEX
    Explanations

    archeology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     facing
    -0.07
     Ups
    -0.06
    (on
    -0.06
     Compile
    -0.06
     WHICH
    -0.06
    desired
    -0.06
     アイ
    -0.06
    	Config
    -0.06
    _Red
    -0.06
    culo
    -0.06
    POSITIVE LOGITS
     SK
    0.07
     میشود
    0.07
     SC
    0.06
    钢
    0.06
    /gr
    0.06
     yerinde
    0.06
     Portsmouth
    0.06
     poi
    0.06
     &:
    0.06
     prospective
    0.06
    Act Density 0.074%

    No Known Activations