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

    Neuronpedia

    INDEX
    Explanations

    accordingly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wednesday
    -0.08
     Ut
    -0.07
    _FD
    -0.07
     Thursday
    -0.07
    MEA
    -0.06
     waste
    -0.06
     HV
    -0.06
    -wave
    -0.06
     Wait
    -0.06
     northern
    -0.06
    POSITIVE LOGITS
     accordingly
    0.10
     Similarly
    0.07
     Accordingly
    0.07
    Similarly
    0.07
    -fashion
    0.06
     отв
    0.06
    指定
    0.06
    关闭
    0.06
    sequently
    0.06
     strategies
    0.06
    Act Density 0.005%

    No Known Activations