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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (`/
    -0.07
     ovšem
    -0.07
    .idea
    -0.06
    люч
    -0.06
     murm
    -0.06
    ¹
    -0.06
    ADDRESS
    -0.06
     SNAP
    -0.06
     isEmpty
    -0.06
     ordinarily
    -0.06
    POSITIVE LOGITS
     happening
    0.08
     troub
    0.07
     transferring
    0.07
     measurable
    0.07
     발
    0.06
    ج
    0.06
     lovely
    0.06
     bị
    0.06
    -contrib
    0.06
     celebration
    0.06
    Act Density 0.004%

    No Known Activations