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

    Neuronpedia

    INDEX
    Explanations

    build

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    quals
    -0.06
    ('');↵
    -0.06
     Tasks
    -0.06
     PDT
    -0.06
     mirrors
    -0.06
    urons
    -0.06
     Punk
    -0.06
     toda
    -0.06
    Valor
    -0.06
    ีข
    -0.06
    POSITIVE LOGITS
    gps
    0.07
     {!
    0.06
    /windows
    0.06
    IBUTES
    0.06
     MaterialPageRoute
    0.06
    (segment
    0.06
    Animating
    0.06
     giải
    0.06
     Regulations
    0.06
    上海
    0.06
    Act Density 0.021%

    No Known Activations