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

    Neuronpedia

    INDEX
    Explanations

    asympt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     influential
    -0.08
     التع
    -0.07
     fresh
    -0.07
     版
    -0.06
     usern
    -0.06
    lardan
    -0.06
     ventilation
    -0.06
     invalid
    -0.06
     rocks
    -0.06
     تن
    -0.06
    POSITIVE LOGITS
     asympt
    0.11
    RT
    0.08
    yr
    0.07
     asym
    0.07
    .y
    0.07
    OMET
    0.07
    AST
    0.07
    ismo
    0.07
    aim
    0.07
     XT
    0.07
    Act Density 0.002%

    No Known Activations