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

    Neuronpedia

    INDEX
    Explanations

    step

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :semicolon
    -0.07
    内の
    -0.06
    Scaler
    -0.06
    elijk
    -0.06
     použít
    -0.06
     slee
    -0.06
    amide
    -0.06
    .lp
    -0.06
    __,__
    -0.06
    Socket
    -0.06
    POSITIVE LOGITS
     steps
    0.09
     step
    0.09
     Step
    0.07
     footsteps
    0.07
     dirig
    0.07
     Steps
    0.07
    0.07
    (text
    0.06
    'field
    0.06
    0.06
    Act Density 0.018%

    No Known Activations