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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     facing
    -0.07
    .components
    -0.07
     AES
    -0.07
    puty
    -0.07
    		
↵
↵
    -0.07
    QUIRE
    -0.07
    ))):↵
    -0.07
    Mine
    -0.07
    piece
    -0.06
     أمر
    -0.06
    POSITIVE LOGITS
     vd
    0.08
     romance
    0.07
    ມ
    0.07
     Esto
    0.07
    ױ
    0.07
     Growth
    0.07
    רן
    0.06
    ório
    0.06
     Elliott
    0.06
    �
    0.06
    Act Density 0.001%

    No Known Activations