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

    Neuronpedia

    INDEX
    Explanations

    replacement or comparison

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MDB
    -0.08
     bson
    -0.08
     lada
    -0.08
     cbd
    -0.08
     snapshot
    -0.07
     kb
    -0.07
    కుండా
    -0.07
     awful
    -0.07
     backups
    -0.07
     Solic
    -0.07
    POSITIVE LOGITS
    της
    0.08
     الهلال
    0.08
     counterpart
    0.08
    角色
    0.08
     counterparts
    0.08
     predstavlj
    0.08
    laget
    0.08
     роль
    0.08
     역할
    0.08
    ४
    0.08
    Act Density 0.024%

    No Known Activations