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

    Neuronpedia

    INDEX
    Explanations

    negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     робота
    -0.08
     ();↵↵
    -0.07
    "?>↵
    -0.07
     ．
    -0.07
    Operation
    -0.06
    compute
    -0.06
     utf
    -0.06
     státy
    -0.06
    task
    -0.06
    vascular
    -0.06
    POSITIVE LOGITS
    相關
    0.07
    IGIN
    0.07
    SHORT
    0.06
     salle
    0.06
    สาร
    0.06
    SSFWorkbook
    0.06
     scent
    0.05
     dick
    0.05
    ùi
    0.05
     Trot
    0.05
    Act Density 0.011%

    No Known Activations