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

    Neuronpedia

    INDEX
    Explanations

    email

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    лагод
    -0.06
    ASCADE
    -0.06
     initiative
    -0.06
     fragmentation
    -0.06
     CIS
    -0.06
     transformer
    -0.06
    946
    -0.06
     resistance
    -0.06
     normalization
    -0.06
     lounge
    -0.06
    POSITIVE LOGITS
     무엇
    0.07
    detail
    0.07
    ?)
    0.06
    rink
    0.06
     ako
    0.06
    /MPL
    0.06
     İlk
    0.06
    私
    0.06
    MODULE
    0.06
    ...");↵↵
    0.06
    Act Density 0.020%

    No Known Activations