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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dimensional
    -0.07
    ROP
    -0.06
    СР
    -0.06
    رش
    -0.06
     spun
    -0.06
     Parkway
    -0.06
    _keyword
    -0.06
    arya
    -0.06
    中华
    -0.06
     Trash
    -0.06
    POSITIVE LOGITS
    "This
    0.07
    “We
    0.07
    Our
    0.07
    "We
    0.06
     graduate
    0.06
     UNION
    0.06
    “These
    0.06
     combine
    0.06
     Our
    0.06
    checking
    0.06
    Act Density 0.024%

    No Known Activations