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

    Neuronpedia

    INDEX
    Explanations

    scenarios

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     पढ़
    -0.80
     auge
    -0.79
    LAX
    -0.79
     Municipalidad
    -0.75
     farinha
    -0.74
     hip
    -0.74
     Azerbaijan
    -0.73
     bañera
    -0.72
    zzjoni
    -0.71
    Armen
    -0.71
    POSITIVE LOGITS
     Scenario
    0.79
    プローチ
    0.79
     scenarios
    0.78
     scenario
    0.77
     レンズ
    0.77
     sureties
    0.76
    scenario
    0.75
     rector
    0.74
    silien
    0.72
     Scenarios
    0.71
    Act Density 0.023%

    No Known Activations