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

    Neuronpedia

    INDEX
    Explanations

    Question marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ourt
    -0.07
     mortality
    -0.06
     Sept
    -0.06
    จะต
    -0.06
     зрост
    -0.06
     Bench
    -0.06
     approvals
    -0.06
     Chemistry
    -0.06
     wit
    -0.06
    _hash
    -0.06
    POSITIVE LOGITS
    /"↵↵
    0.07
    tri
    0.07
    _IMP
    0.07
     Daten
    0.06
    URLConnection
    0.06
    ##↵↵
    0.06
     คณะ
    0.06
    declar
    0.06
     naï
    0.06
     menj
    0.06
    Act Density 0.004%

    No Known Activations