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

    Neuronpedia

    INDEX
    Explanations

    corner

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    price
    -0.07
    _reply
    -0.06
     layer
    -0.06
     pdb
    -0.06
     Wikispecies
    -0.06
    ublished
    -0.06
     пас
    -0.06
     navigation
    -0.06
    emory
    -0.06
     frustrated
    -0.06
    POSITIVE LOGITS
    」の
    0.07
    щают
    0.06
    =''):↵
    0.06
    の上
    0.06
    스의
    0.06
    illos
    0.06
     každý
    0.06
     Negative
    0.06
    -terminal
    0.06
    čemž
    0.06
    Act Density 0.008%

    No Known Activations