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

    Neuronpedia

    INDEX
    Explanations

    model evaluation scores

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .default
    -0.08
    _editor
    -0.07
    .notify
    -0.06
     salvage
    -0.06
     云
    -0.06
    iants
    -0.06
     सह
    -0.06
    .package
    -0.06
     modulus
    -0.06
     aggregates
    -0.06
    POSITIVE LOGITS
     }}>↵
    0.07
     Discuss
    0.06
    ное
    0.06
     Offer
    0.06
     Banks
    0.06
    лив
    0.06
    Segoe
    0.06
    Press
    0.06
     adversely
    0.06
     Rifle
    0.06
    Act Density 0.015%

    No Known Activations