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

    Neuronpedia

    INDEX
    Explanations

    machinery

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stakes
    -0.06
    iggers
    -0.06
    abilities
    -0.06
    Adding
    -0.06
    >-->↵
    -0.06
    'am
    -0.06
     дело
    -0.06
     уд
    -0.06
     物
    -0.06
    коз
    -0.06
    POSITIVE LOGITS
     machinery
    0.09
     Machinery
    0.08
     gra
    0.07
    smooth
    0.07
     horse
    0.07
     Horse
    0.06
    Free
    0.06
     Gra
    0.06
    classifier
    0.06
     meditation
    0.06
    Act Density 0.011%

    No Known Activations