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

    Neuronpedia

    INDEX
    Explanations

    machines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hx
    -0.09
     ambassador
    -0.08
     denunciar
    -0.07
    Dv
    -0.07
     investi
    -0.07
     reimbursement
    -0.07
    wv
    -0.07
     đỏ
    -0.07
     ulcer
    -0.07
     cozy
    -0.07
    POSITIVE LOGITS
     machinery
    0.12
     gears
    0.12
    机械
    0.11
     آلات
    0.11
    Mechanical
    0.10
     Machinery
    0.10
    机制
    0.10
     maquinaria
    0.10
     mecan
    0.10
     malfunction
    0.10
    Act Density 0.062%

    No Known Activations