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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �p
    -0.06
    Publication
    -0.06
    DetailsService
    -0.06
     pairing
    -0.06
     信
    -0.06
     determin
    -0.06
     '',↵
    -0.05
     diversity
    -0.05
    Helmet
    -0.05
     شاه
    -0.05
    POSITIVE LOGITS
     Reset
    0.07
     спроб
    0.07
    _lowercase
    0.07
     사업
    0.07
    prit
    0.07
    itles
    0.07
    орож
    0.07
    /login
    0.06
    gos
    0.06
     BRO
    0.06
    Act Density 0.321%

    No Known Activations