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

    Neuronpedia

    INDEX
    Explanations

    research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    唯一
    -0.07
     captive
    -0.07
    agli
    -0.06
    side
    -0.06
     astronaut
    -0.06
     Isle
    -0.06
     Sher
    -0.06
     DESCRIPTION
    -0.06
     والد
    -0.06
     信
    -0.06
    POSITIVE LOGITS
    “We
    0.07
     =~
    0.06
    :`~
    0.06
    ijn
    0.06
    italic
    0.06
    �
    0.06
    Come
    0.06
     člově
    0.06
     Career
    0.06
     cord
    0.06
    Act Density 0.181%

    No Known Activations