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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kỹ
    -0.07
    [arg
    -0.07
     stole
    -0.07
     Humb
    -0.07
    thumbnail
    -0.07
     sist
    -0.06
    .Signal
    -0.06
    keyboard
    -0.06
    /antlr
    -0.06
    flows
    -0.06
    POSITIVE LOGITS
     upd
    0.07
    null
    0.06
     LJ
    0.06
     LEN
    0.06
     Nov
    0.06
     barcelona
    0.06
    rolley
    0.06
     incident
    0.06
    v
    0.05
     Brisbane
    0.05
    Act Density 0.008%

    No Known Activations