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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sleep
    -0.08
     Velocity
    -0.07
     thống
    -0.07
    editable
    -0.06
     bite
    -0.06
     waves
    -0.06
     nausea
    -0.06
    posing
    -0.06
     nova
    -0.06
    -rock
    -0.06
    POSITIVE LOGITS
    ————————
    0.07
     complic
    0.06
     inspections
    0.06
     ^{}
    0.06
    �
    0.06
    �
    0.06
    userService
    0.06
    ocumented
    0.06
    947
    0.06
    以为
    0.06
    Act Density 0.033%

    No Known Activations