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

    Neuronpedia

    INDEX
    Explanations

    active

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Write
    -0.07
    �
    -0.07
     Folder
    -0.07
    Reporter
    -0.07
    ECTOR
    -0.06
     theatre
    -0.06
     Canary
    -0.06
     Economics
    -0.06
    -bal
    -0.06
    retty
    -0.06
    POSITIVE LOGITS
    ////////////////////////////////////////////////////////////////////////////////↵
    0.07
    сих
    0.06
     उपय
    0.06
    [param
    0.06
     @"";↵
    0.06
     غ
    0.06
    FromBody
    0.06
    ोट
    0.06
    ...");↵
    0.06
     професси
    0.06
    Act Density 0.023%

    No Known Activations