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

    Neuronpedia

    INDEX
    Explanations

    code and data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     adversaries
    -0.07
     sobie
    -0.07
     storia
    -0.07
    ैर
    -0.06
     harvesting
    -0.06
     cheeses
    -0.06
     trava
    -0.06
    组
    -0.06
     такі
    -0.06
    _pas
    -0.06
    POSITIVE LOGITS
     You
    0.06
    ATUS
    0.06
     Picker
    0.06
     Startup
    0.06
    abilité
    0.06
     VB
    0.06
    urple
    0.06
     über
    0.06
    ichick
    0.06
    .Language
    0.06
    Act Density 0.065%

    No Known Activations