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

    Neuronpedia

    INDEX
    Explanations

    Offers or resources found

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ideally
    -0.07
    ̧
    -0.06
    different
    -0.06
    _retry
    -0.06
    species
    -0.06
    агато
    -0.06
     університет
    -0.06
     können
    -0.06
     kwargs
    -0.06
    $model
    -0.06
    POSITIVE LOGITS
    ...↵
    0.07
    641
    0.07
    Responder
    0.07
    -maker
    0.07
    ....↵
    0.06
    ennifer
    0.06
    Bid
    0.06
    $$
    0.06
     URLs
    0.06
    ίσ
    0.06
    Act Density 0.016%

    No Known Activations