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

    Neuronpedia

    INDEX
    Explanations

    setting parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Gardens
    0.41
     Beach
    0.39
    Heaven
    0.38
    ध्ये
    0.38
    Improving
    0.37
     Horseshoe
    0.37
    ەوە
    0.37
    Ancient
    0.37
    Carol
    0.37
     Economics
    0.36
    POSITIVE LOGITS
     comprobar
    0.49
     cadastro
    0.45
     atualizar
    0.45
     параметры
    0.45
     validar
    0.45
     enviar
    0.44
     actualizar
    0.44
     sincron
    0.44
     asignar
    0.44
     координаты
    0.44
    Act Density 0.069%

    No Known Activations