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

    Neuronpedia

    INDEX
    Explanations

    .POST

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    service
    -0.08
    shelf
    -0.07
    jíž
    -0.07
    Fair
    -0.06
     expo
    -0.06
     destroyed
    -0.06
     عم
    -0.06
     costing
    -0.06
     bey
    -0.06
     barbecue
    -0.06
    POSITIVE LOGITS
    sync
    0.07
     Scarlett
    0.07
    Selective
    0.07
    .Dynamic
    0.06
     पर
    0.06
    總
    0.06
    (TreeNode
    0.06
    。「
    0.06
    .Redis
    0.06
    oon
    0.06
    Act Density 0.001%

    No Known Activations