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

    Neuronpedia

    INDEX
    Explanations

    suggestions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Crushing
    -0.08
     Sorry
    -0.07
    _Db
    -0.07
    Courses
    -0.07
     stop
    -0.07
     surfaces
    -0.06
     Twelve
    -0.06
     Problems
    -0.06
    Delay
    -0.06
     prosecuting
    -0.06
    POSITIVE LOGITS
    office
    0.06
    SCII
    0.06
    mue
    0.06
    олее
    0.06
     výbě
    0.06
    .O
    0.06
    ético
    0.06
     testcase
    0.06
     cyber
    0.06
    ScrollIndicator
    0.06
    Act Density 0.072%

    No Known Activations