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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Following
    -0.07
    Following
    -0.07
     than
    -0.07
     orch
    -0.06
    "While
    -0.06
    "g
    -0.06
     Pork
    -0.06
     Agencies
    -0.06
     encompasses
    -0.06
     Dining
    -0.06
    POSITIVE LOGITS
    ستم
    0.07
     στι
    0.06
     chambre
    0.06
    .launch
    0.06
     ninguna
    0.06
    _imgs
    0.06
    ॉप
    0.06
    避
    0.06
     Cocoa
    0.06
    (lua
    0.06
    Act Density 0.018%

    No Known Activations