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

    Neuronpedia

    INDEX
    Explanations

    Code color definitions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ']."
    -0.07
     وسط
    -0.06
     Eq
    -0.06
    -legged
    -0.06
    pios
    -0.06
     totally
    -0.06
    ければ
    -0.06
    ､_
    -0.06
     hypothetical
    -0.06
    유머
    -0.06
    POSITIVE LOGITS
     trustworthy
    0.07
     proficiency
    0.07
     estruct
    0.07
     Picture
    0.07
     стар
    0.06
    paring
    0.06
    Orth
    0.06
    /save
    0.06
    \Command
    0.06
     euth
    0.06
    Act Density 0.004%

    No Known Activations