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

    Neuronpedia

    INDEX
    Explanations

    code/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Monterey
    -0.07
    -Version
    -0.07
     conscious
    -0.07
     Agenda
    -0.07
     dissip
    -0.06
    .Sound
    -0.06
     deed
    -0.06
     theorists
    -0.06
     psychologists
    -0.06
    .Reverse
    -0.06
    POSITIVE LOGITS
    '
↵
↵
    0.07
    Axis
    0.07
    venile
    0.06
    ↵↵
    0.06
    샵
    0.05
    ा↵
    0.05
     deliberately
    0.05
    ávají
    0.05
    �
    0.05
    amon
    0.05
    Act Density 0.193%

    No Known Activations