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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hunted
    -0.07
     Caucasian
    -0.07
     planted
    -0.07
     лес
    -0.07
     social
    -0.06
    Digits
    -0.06
    ुह
    -0.06
    겼
    -0.06
     cairo
    -0.06
     Δε
    -0.06
    POSITIVE LOGITS
    	ASSERT
    0.07
    ape
    0.06
    (slug
    0.06
    (port
    0.06
    _decimal
    0.05
     Node
    0.05
     　　　　　　　　
    0.05
    **,
    0.05
     хви
    0.05
     chave
    0.05
    Act Density 0.016%

    No Known Activations