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

    Neuronpedia

    INDEX
    Explanations

    Rails code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     endTime
    -0.07
    [OF
    -0.07
     flavored
    -0.06
     BBQ
    -0.06
     preference
    -0.06
    Shopping
    -0.06
     hiking
    -0.06
    Criterion
    -0.06
     Nath
    -0.06
    Sq
    -0.06
    POSITIVE LOGITS
     Vi
    0.07
     valida
    0.07
    missions
    0.07
     Constit
    0.06
    ält
    0.06
    LESS
    0.06
    istant
    0.06
     Recently
    0.06
    िलत
    0.06
    Allows
    0.06
    Act Density 0.005%

    No Known Activations