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

    Neuronpedia

    INDEX
    Explanations

    reception

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    COLOUR
    -1.53
     Initialise
    -1.53
     initialise
    -1.48
    Ещё
    -1.47
    personalised
    -1.46
     customised
    -1.43
    authorised
    -1.43
    initialise
    -1.43
    behaviour
    -1.42
     visualisation
    -1.42
    POSITIVE LOGITS
    ↵↵
    0.92
     
    0.90
     .
    0.73
    .
    0.72
     The
    0.72
      
    0.68
     A
    0.68
     F
    0.64
     W
    0.60
    '
    0.59
    Act Density 0.267%

    No Known Activations