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

    Neuronpedia

    INDEX
    Explanations

    structure assembly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     RP
    -0.07
    _PLAYER
    -0.07
     Guill
    -0.07
    .maxLength
    -0.06
    端
    -0.06
     Edward
    -0.06
     управления
    -0.06
    -addons
    -0.06
     Executes
    -0.06
    chedulers
    -0.06
    POSITIVE LOGITS
    (Employee
    0.07
    esse
    0.07
    RITE
    0.06
    rite
    0.06
     excluding
    0.06
    UDGE
    0.06
    .,
    0.06
     benefits
    0.06
     Consumption
    0.06
     매매
    0.06
    Act Density 0.024%

    No Known Activations