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

    Neuronpedia

    INDEX
    Explanations

    planning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     authService
    -0.07
    すべて
    -0.07
     |_|
    -0.06
    ури
    -0.06
    (By
    -0.06
    _receipt
    -0.06
    为了
    -0.06
    úb
    -0.06
    iterals
    -0.06
    DAO
    -0.06
    POSITIVE LOGITS
     separators
    0.07
     Dating
    0.06
    _birth
    0.06
    iolet
    0.06
    _jump
    0.06
     marker
    0.06
     Residence
    0.06
     offset
    0.06
     legitimately
    0.06
    言
    0.06
    Act Density 0.004%

    No Known Activations