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

    Neuronpedia

    INDEX
    Explanations

    .display

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    BBBB
    -0.07
    .ak
    -0.07
    Fallback
    -0.07
     realistically
    -0.06
     MMM
    -0.06
    dou
    -0.06
     \$
    -0.06
    Character
    -0.06
    MainActivity
    -0.06
     juicy
    -0.06
    POSITIVE LOGITS
    یشه
    0.07
    neğin
    0.06
     péče
    0.06
    acted
    0.06
    uptools
    0.06
     checking
    0.06
     daň
    0.06
    empl
    0.06
    continuous
    0.06
    reak
    0.06
    Act Density 0.002%

    No Known Activations