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

    Neuronpedia

    INDEX
    Explanations

    computer instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PRESS
    -0.06
     truthful
    -0.06
    907
    -0.06
    |↵
    -0.06
    Selectors
    -0.06
     ass
    -0.06
     fold
    -0.06
     Families
    -0.06
     Expense
    -0.06
     Fast
    -0.06
    POSITIVE LOGITS
    .Down
    0.08
     adverts
    0.07
    “She
    0.07
    epad
    0.06
    panels
    0.06
    Bullet
    0.06
    'y
    0.06
     Accent
    0.06
    ’y
    0.06
    _marshaled
    0.06
    Act Density 0.224%

    No Known Activations