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

    Neuronpedia

    INDEX
    Explanations

    Is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     equipos
    -0.07
    cin
    -0.07
    нер
    -0.07
    dbus
    -0.07
    .sponge
    -0.06
     mente
    -0.06
    elopment
    -0.06
     snake
    -0.06
    当
    -0.06
    cly
    -0.06
    POSITIVE LOGITS
     belonging
    0.07
     Is
    0.07
     MessageType
    0.06
    (Is
    0.06
    .rightBarButtonItem
    0.06
     หม
    0.06
    itives
    0.06
    ()")↵
    0.06
    助
    0.06
    lant
    0.06
    Act Density 0.007%

    No Known Activations