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
    arin
    -0.08
    Fold
    -0.07
    Queue
    -0.07
     requests
    -0.07
    .mockito
    -0.07
    days
    -0.07
    romě
    -0.07
     ankles
    -0.06
    っ
    -0.06
    quotes
    -0.06
    POSITIVE LOGITS
    (nodes
    0.06
    (userId
    0.06
     garg
    0.06
    ッツ
    0.06
     MSM
    0.06
     elementos
    0.06
    ",
↵
    0.06
     bfd
    0.06
     stab
    0.06
     Homework
    0.05
    Act Density 0.082%

    No Known Activations