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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     loaf
    -0.07
     tongue
    -0.07
     piece
    -0.07
     Income
    -0.07
     lan
    -0.07
     whole
    -0.06
     claw
    -0.06
     tongues
    -0.06
    Bright
    -0.06
    .bin
    -0.06
    POSITIVE LOGITS
    ecký
    0.07
    onis
    0.07
    frauen
    0.06
    Milliseconds
    0.06
     ↵  ↵
    0.06
    Thrown
    0.06
    ."↵↵↵↵
    0.06
    .ENTER
    0.06
    <const
    0.06
    ！」
    0.06
    Act Density 0.012%

    No Known Activations