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

    Neuronpedia

    INDEX
    Explanations

    target

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Todo
    -0.07
    Mother
    -0.07
     Kürt
    -0.06
    ecurity
    -0.06
    numbers
    -0.06
     Hindus
    -0.06
    ルド
    -0.06
     Cake
    -0.06
     resist
    -0.06
     रस
    -0.06
    POSITIVE LOGITS
    getic
    0.06
     mới
    0.06
    ][-
    0.06
    thy
    0.06
    	ext
    0.06
    -name
    0.06
    Staff
    0.06
    已经
    0.06
    -associated
    0.06
     seriousness
    0.06
    Act Density 0.009%

    No Known Activations