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

    Neuronpedia

    INDEX
    Explanations

    diss

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (UInt
    -0.07
     wlan
    -0.07
     Metropolitan
    -0.07
     llevar
    -0.07
    starting
    -0.07
    ião
    -0.06
    _HEALTH
    -0.06
    :',
    -0.06
    +f
    -0.06
    .drawable
    -0.06
    POSITIVE LOGITS
    iss
    0.10
    ISS
    0.08
    -loss
    0.07
    CESS
    0.07
    VERS
    0.06
    essa
    0.06
    Boss
    0.06
     Weiss
    0.06
     Participant
    0.06
    loss
    0.06
    Act Density 0.035%

    No Known Activations