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

    Neuronpedia

    INDEX
    Explanations

    years

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _CONF
    -0.08
    tron
    -0.07
    jem
    -0.07
     fermentation
    -0.07
     freedom
    -0.07
    _cert
    -0.07
    _compress
    -0.07
    Freedom
    -0.06
    سط
    -0.06
    atron
    -0.06
    POSITIVE LOGITS
    (['
    0.07
    =[]
↵
    0.07
     sondern
    0.06
    \E
    0.06
     �
    0.06
    PRE
    0.06
     как
    0.06
    COVID
    0.06
     adversary
    0.06
    (inplace
    0.06
    Act Density 0.044%

    No Known Activations