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

    Neuronpedia

    INDEX
    Explanations

    prime factors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SCO
    -0.07
    topic
    -0.07
     onSubmit
    -0.07
    �
    -0.06
    	BOOST
    -0.06
    676
    -0.06
    Congratulations
    -0.06
    ERO
    -0.06
     respawn
    -0.06
    includes
    -0.06
    POSITIVE LOGITS
     prejudices
    0.06
     athletics
    0.06
    사는
    0.06
     Dependency
    0.06
     tiếng
    0.06
     электри
    0.06
     обуч
    0.06
     mức
    0.06
    .transport
    0.06
    […
    0.06
    Act Density 0.003%

    No Known Activations