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

    Neuronpedia

    INDEX
    Explanations

    No compromise or exceptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .INVISIBLE
    -0.08
    monton
    -0.08
     Dumbledore
    -0.07
     comunità
    -0.07
    葰
    -0.07
    anonymous
    -0.07
    isOpen
    -0.07
    (INVOKE
    -0.07
     simple
    -0.07
    .available
    -0.07
    POSITIVE LOGITS
    doc
    0.07
     impatient
    0.07
    𝐨
    0.07
     ridiculous
    0.06
     lunch
    0.06
     thị
    0.06
    elastic
    0.06
    Chart
    0.06
     estudio
    0.06
    andal
    0.06
    Act Density 0.084%

    No Known Activations