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

    Neuronpedia

    INDEX
    Explanations

    different

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    æī£
    -0.31
    åħ¶ä»ĸçļĦ
    -0.30
    åħ¶ä»ĸ
    -0.29
     verw
    -0.28
    adoras
    -0.28
    other
    -0.26
    owns
    -0.26
    /*@
    -0.25
    athe
    -0.25
    folders
    -0.24
    POSITIVE LOGITS
     sample
    0.31
     story
    0.30
     arena
    0.28
    UED
    0.28
     scenario
    0.28
     occasion
    0.27
     approach
    0.26
     trail
    0.26
    ials
    0.25
    å®īæİĴ
    0.25
    Act Density 0.019%

    No Known Activations