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

    Neuronpedia

    INDEX
    Explanations

    more or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pfizer
    -0.07
    rani
    -0.06
     Des
    -0.06
     woo
    -0.06
     desi
    -0.06
    _IDS
    -0.06
    .interface
    -0.06
     Pork
    -0.06
    775
    -0.06
     Composition
    -0.06
    POSITIVE LOGITS
    Annotation
    0.07
     }}">↵
    0.07
    _wait
    0.06
     tear
    0.06
     ipad
    0.06
    ")));↵↵
    0.06
    ell
    0.06
     ماند
    0.06
    ляют
    0.06
    LOCKS
    0.06
    Act Density 0.004%

    No Known Activations