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

    Neuronpedia

    INDEX
    Explanations

    hobbes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     directement
    -0.08
     richtigen
    -0.08
     direkte
    -0.08
    utari
    -0.08
    871
    -0.08
     direkten
    -0.08
    导演
    -0.08
    -songwriter
    -0.07
    .direct
    -0.07
    206
    -0.07
    POSITIVE LOGITS
     Corps
    0.08
     ECS
    0.08
    .Editor
    0.08
     corps
    0.08
     Pax
    0.07
     Lord
    0.07
     eder
    0.07
     взгляд
    0.07
    ziger
    0.07
    ischer
    0.07
    Act Density 0.000%

    No Known Activations