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

    Neuronpedia

    INDEX
    Explanations

    code and server configuration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Brut
    -0.07
    ell
    -0.06
    agg
    -0.06
     ActiveSupport
    -0.06
     schl
    -0.06
    unn
    -0.06
    _Request
    -0.06
    _sms
    -0.06
     Mö
    -0.06
    нер
    -0.06
    POSITIVE LOGITS
     Determines
    0.06
    mobile
    0.06
     lament
    0.06
     disturbances
    0.06
     seated
    0.06
     Yesterday
    0.06
    رفت
    0.06
     capacities
    0.06
     account
    0.06
     unidades
    0.06
    Act Density 0.035%

    No Known Activations