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

    Neuronpedia

    INDEX
    Explanations

    names following "came"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     H
    0.46
     K
    0.46
     P
    0.42
     W
    0.42
     L
    0.40
     J
    0.40
     D
    0.39
     S
    0.38
     M
    0.37
     G
    0.37
    POSITIVE LOGITS
    Denote
    0.36
     preprocess
    0.35
    Melitaea
    0.35
     `=`
    0.34
    Therates
    0.33
    Encoding
    0.32
    Conformance
    0.32
    0.32
     subspaces
    0.32
     आल्स
    0.32
    Act Density 0.007%

    No Known Activations