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

    Neuronpedia

    INDEX
    Explanations

    pragma and #![ attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     moistened
    0.41
    ger
    0.41
     FTP
    0.38
    dale
    0.37
    chi
    0.36
    peter
    0.36
     Lafayette
    0.36
    ak
    0.36
     offered
    0.35
    jog
    0.35
    POSITIVE LOGITS
    pragma
    0.55
     directives
    0.55
    愼
    0.50
    ScriptName
    0.50
     directive
    0.49
    #![
    0.48
     prag
    0.46
     importa
    0.45
     declarations
    0.44
     #-}
    0.44
    Act Density 0.010%

    No Known Activations