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

    Neuronpedia

    INDEX
    Explanations

    does

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    olta
    -0.09
     Masa
    -0.08
     fruitful
    -0.08
     breakthroughs
    -0.08
     Pos
    -0.08
     zainteres
    -0.08
    .Pos
    -0.07
     Quai
    -0.07
     contempt
    -0.07
    953
    -0.07
    POSITIVE LOGITS
     stap
    0.08
     автоматически
    0.08
     capabilities
    0.08
    Basically
    0.08
     precies
    0.08
     automatisch
    0.08
     exactement
    0.08
     couvrir
    0.07
    :↵//
    0.07
    Π
    0.07
    Act Density 0.025%

    No Known Activations