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

    Neuronpedia

    INDEX
    Explanations

    code/paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ικός
    -0.09
     xpos
    -0.07
     dese
    -0.06
    nonce
    -0.06
    итив
    -0.06
     tweets
    -0.06
    -null
    -0.06
    τών
    -0.06
    stash
    -0.06
     Thur
    -0.06
    POSITIVE LOGITS
     recounted
    0.06
    ,/
    0.06
     activist
    0.06
    олот
    0.06
    abort
    0.06
     MW
    0.06
    'ai
    0.06
     enforcing
    0.06
     masa
    0.06
     Raymond
    0.06
    Act Density 0.008%

    No Known Activations