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

    Neuronpedia

    INDEX
    Explanations

    sending information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mCurrent
    -0.06
     detected
    -0.06
     mang
    -0.06
     erhalten
    -0.06
     premise
    -0.06
     song
    -0.06
     character
    -0.06
     выбра
    -0.05
     identify
    -0.05
     deceived
    -0.05
    POSITIVE LOGITS
     goalie
    0.07
    .environment
    0.07
     Peters
    0.07
     Aff
    0.07
    [op
    0.07
     rumored
    0.07
    049
    0.07
    RELATED
    0.07
     taxing
    0.06
    Press
    0.06
    Act Density 0.058%

    No Known Activations