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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     targeting
    -0.06
    .pk
    -0.06
     escalated
    -0.06
     toplam
    -0.06
    >]
    -0.06
     kepada
    -0.06
     modificar
    -0.06
    ução
    -0.06
     immersed
    -0.06
     sidl
    -0.05
    POSITIVE LOGITS
     Daniel
    0.07
    essaging
    0.07
     Tro
    0.07
    assel
    0.06
     Authorization
    0.06
    élé
    0.06
     Điều
    0.06
    486
    0.06
     Monter
    0.06
    buff
    0.06
    Act Density 0.001%

    No Known Activations